Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    positive descriptions of experiences and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a number, bracket, or punctuation

    np_acts-logits-general · gemini-2.0-flash

    positive sentiment in mathematical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.70
     تضيفلها
    -0.60
     Italijanski
    -0.59
     AssemblyProduct
    -0.58
    UnsafeEnabled
    -0.58
    GEBURTS
    -0.58
     ब्रेकडाउन
    -0.57
     tranſ
    -0.57
     againſt
    -0.56
     Administrativna
    -0.56
    POSITIVE LOGITS
     excellent
    0.41
     angene
    0.39
     wonderful
    0.37
     dodat
    0.36
     hilfre
    0.36
     👌
    0.36
     thoughtful
    0.36
     great
    0.36
    .*")]
    0.35
     ️
    0.35
    Act Density 0.139%

    No Known Activations