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

    Neuronpedia

    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Responsive
    -0.06
    Cars
    -0.06
    .runner
    -0.06
     grids
    -0.06
    وال
    -0.06
    ्व
    -0.06
    odata
    -0.06
    gent
    -0.06
    acked
    -0.06
    *pi
    -0.06
    POSITIVE LOGITS
     отк
    0.06
     zakáz
    0.06
    ≧
    0.06
     /////
    0.06
     Mé
    0.06
    /N
    0.06
     vlak
    0.06
    Catalog
    0.06
    _only
    0.06
     terug
    0.06
    Act Density 0.005%

    No Known Activations