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

    Neuronpedia

    INDEX
    Explanations

    enumerating individual items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.43
    Ac
    0.34
    {
    0.33
    essoas
    0.32
    smöglichkeiten
    0.32
    -{
    0.32
     frumo
    0.31
     այ
    0.30
     Âu
    0.30
    n
    0.30
    POSITIVE LOGITS
     einzelnen
    0.63
     einzelne
    0.60
     jednotliv
    0.55
     respective
    0.54
     each
    0.53
    Each
    0.52
    每个
    0.47
     Each
    0.47
     EACH
    0.46
     每个
    0.46
    Act Density 0.044%

    No Known Activations