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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     im
    -0.07
     eing
    -0.06
     inp
    -0.06
    _nl
    -0.06
     ци
    -0.06
    .pagination
    -0.06
     totaled
    -0.06
     sert
    -0.06
     pharmac
    -0.06
     gives
    -0.06
    POSITIVE LOGITS
    احل
    0.07
    μμε
    0.07
    ційні
    0.06
    .sulake
    0.06
    FUL
    0.06
    _thumbnail
    0.06
     conexión
    0.06
    edriver
    0.06
     değildir
    0.06
    azers
    0.06
    Act Density 0.002%

    No Known Activations