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

    Neuronpedia

    INDEX
    Explanations

    blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ΑΝΤ
    -0.06
    Lex
    -0.06
     chế
    -0.06
    회
    -0.06
    �
    -0.06
    ği
    -0.06
    DMIN
    -0.06
    �
    -0.06
    osloven
    -0.05
    нику
    -0.05
    POSITIVE LOGITS
    _Array
    0.07
     manufacturers
    0.07
    –and
    0.07
     Milwaukee
    0.07
    ,!
    0.07
    ']).
    0.07
     ----------------------------------------------------------------------↵
    0.07
    _action
    0.06
    _MB
    0.06
    |max
    0.06
    Act Density 0.000%

    No Known Activations