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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _norm
    -0.06
     oct
    -0.06
     prim
    -0.06
    �
    -0.06
     opt
    -0.06
     Morgan
    -0.06
    _effect
    -0.06
     плав
    -0.06
     三
    -0.06
    仰
    -0.06
    POSITIVE LOGITS
    otten
    0.07
     <|
    0.07
    %"),↵
    0.07
    ,False
    0.06
    ’nun
    0.06
    فصل
    0.06
     edip
    0.06
     söyledi
    0.06
     ikt
    0.06
     О
    0.06
    Act Density 0.126%

    No Known Activations