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

    Neuronpedia

    INDEX
    Explanations

    lists and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setPassword
    -0.08
     gaming
    -0.07
     Cipher
    -0.07
    _SORT
    -0.06
     setHidden
    -0.06
    aptcha
    -0.06
     uy
    -0.06
    .SizeF
    -0.06
     ไทย
    -0.06
     đ�
    -0.06
    POSITIVE LOGITS
     Improved
    0.07
    udi
    0.06
     exposition
    0.06
    ۰۰
    0.06
    Presence
    0.06
    enerate
    0.06
    Dialogue
    0.06
     موسیقی
    0.06
     tijd
    0.06
    indices
    0.06
    Act Density 0.233%

    No Known Activations