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

    Neuronpedia

    INDEX
    Explanations

    open and close parentheses in code segments

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

    <start_of_turn>user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.63
    fjspx
    -0.57
     Administrativna
    -0.57
     CURIAM
    -0.56
     AssemblyCompany
    -0.56
    enterOuterAlt
    -0.56
     فريبيس
    -0.55
     BorderRadius
    -0.54
     agrí
    -0.51
     &___
    -0.51
    POSITIVE LOGITS
     dibawah
    0.48
     navidad
    0.46
     didalam
    0.46
     eğer
    0.45
     Eğer
    0.45
     uñas
    0.44
     étoient
    0.43
     Apabila
    0.42
     if
    0.41
     perchè
    0.41
    Act Density 0.005%

    No Known Activations