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

    Neuronpedia

    INDEX
    Explanations

    also not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    İ
    0.50
    I
    0.48
    uber
    0.47
     Ledger
    0.47
    et
    0.47
     Pok
    0.45
    W
    0.45
     Kobayashi
    0.45
     Landing
    0.45
     Ranch
    0.44
    POSITIVE LOGITS
     educating
    0.63
     educate
    0.52
     académico
    0.51
     отда
    0.49
    蹊
    0.49
     educativos
    0.49
    motionProxy
    0.49
    $&$-
    0.48
    quefois
    0.48
     acque
    0.47
    Act Density 0.001%

    No Known Activations