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

    Neuronpedia

    INDEX
    Explanations

    phrases involving positive adjectives and descriptors

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

    article or very preceding adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disambiguazione
    -0.38
    isinstance
    -0.38
    Reflection
    -0.37
    directories
    -0.36
     Reflection
    -0.36
    guém
    -0.36
    others
    -0.35
    inference
    -0.35
    falen
    -0.35
    ๆ
    -0.35
    POSITIVE LOGITS
    IBOutlet
    0.66
    SourceChecksum
    0.59
    IVEREF
    0.59
     FetchType
    0.56
     unbeatable
    0.52
     widest
    0.51
     strong
    0.50
     vast
    0.49
     MonoBehaviour
    0.49
     expansive
    0.49
    Act Density 0.013%

    No Known Activations