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

    Neuronpedia

    INDEX
    Explanations

    Autoregressive forecasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Permit
    1.09
    Candy
    1.01
     Gewer
    1.00
    Чу
    0.99
    isRequired
    0.99
     Dispute
    0.98
    req
    0.97
    Diffuse
    0.97
     This
    0.97
    nCurrent
    0.95
    POSITIVE LOGITS
    mes
    1.40
    entious
    1.37
    ゲット
    1.29
     eyep
    1.29
    ciones
    1.29
    utos
    1.25
    agem
    1.25
     receptions
    1.25
    厚生
    1.25
     hatches
    1.24
    Act Density 0.301%

    No Known Activations