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

    Neuronpedia

    INDEX
    Explanations

    Cybill Shepherd presses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    1.08
    y
    0.97
    et
    0.94
    el
    0.89
    lab
    0.85
    iched
    0.84
     st
    0.82
    eture
    0.82
    edi
    0.80
    emb
    0.79
    POSITIVE LOGITS
     sovereigns
    0.90
    vég
    0.88
    ักษณะ
    0.86
     koja
    0.82
     कथन
    0.82
     która
    0.81
    Strategies
    0.79
     ninguna
    0.79
     भाभी
    0.79
    formatted
    0.78
    Act Density 0.000%

    No Known Activations