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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teeth
    -0.07
     Booth
    -0.07
     Accred
    -0.06
    县
    -0.06
     salads
    -0.06
     enorm
    -0.06
    难
    -0.06
    _system
    -0.06
     recomm
    -0.06
     trabaj
    -0.06
    POSITIVE LOGITS
    68
    0.08
    �
    0.07
    69
    0.07
    şk
    0.07
     Kirby
    0.07
     går
    0.07
    _crossentropy
    0.07
    �
    0.07
    ROUTE
    0.07
    clude
    0.07
    Act Density 0.022%

    No Known Activations