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
    GameOver
    -0.07
    coeff
    -0.07
     Experiment
    -0.06
    project
    -0.06
     STDMETHODCALLTYPE
    -0.06
    startup
    -0.06
    Sad
    -0.06
     Sad
    -0.06
     производ
    -0.06
     rowspan
    -0.06
    POSITIVE LOGITS
    416
    0.08
     Faith
    0.06
    precation
    0.06
     Roth
    0.06
    .console
    0.06
    gent
    0.06
     shotgun
    0.06
     Glouce
    0.06
    सभ
    0.06
    \xa
    0.06
    Act Density 0.001%

    No Known Activations