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

    Neuronpedia

    INDEX
    Explanations

    form submission buttons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imshow
    0.73
    taker
    0.70
    ットン
    0.69
     peculi
    0.65
    h
    0.64
    v
    0.63
    blom
    0.61
    titleTextStyle
    0.61
    n
    0.61
     bagel
    0.61
    POSITIVE LOGITS
    </td>
    0.84
    ="
    0.82
    ł
    0.82
    </h3>
    0.81
    น้ำ
    0.80
    ın
    0.77
    로
    0.72
     badań
    0.71
    น
    0.71
    ção
    0.70
    Act Density 0.005%

    No Known Activations