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

    Neuronpedia

    INDEX
    Explanations

    Buenos Aires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    コツ
    1.38
     of
    1.29
    例文帳に追加
    1.22
    vorschau
    1.20
    ’
    1.18
    '
    1.18
     evidence
    1.18
     must
    1.17
    ouncement
    1.17
    jenigen
    1.14
    POSITIVE LOGITS
    Diffuse
    2.36
     субъек
    2.04
    leftrightarrow
    2.02
    thickness
    1.98
    whelming
    1.96
    compens
    1.95
    ترل
    1.93
    multipart
    1.93
    whel
    1.91
    resonant
    1.87
    Act Density 0.191%

    No Known Activations