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

    Neuronpedia

    INDEX
    Explanations

    form submission actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    らを
    0.49
    anaf
    0.49
    }-${
    0.49
    ogenen
    0.48
    ㎛
    0.48
    olf
    0.48
    łaś
    0.48
    ธอ
    0.48
    гө
    0.47
    hoz
    0.47
    POSITIVE LOGITS
     Darüber
    0.45
     Saud
    0.44
    B
    0.44
    ்த்த
    0.44
     Davies
    0.43
     Connie
    0.43
     Blair
    0.43
     mlijeka
    0.43
     violência
    0.42
     Premi
    0.42
    Act Density 0.001%

    No Known Activations