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

    Neuronpedia

    INDEX
    Explanations

    orable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ヅ
    -0.07
    姶
    -0.07
     désir
    -0.07
    仓储
    -0.07
    滗
    -0.06
     WITH
    -0.06
    イヤ
    -0.06
    abric
    -0.06
    haus
    -0.06
     burgeoning
    -0.06
    POSITIVE LOGITS
    本
    0.08
     procedure
    0.07
    本基金
    0.07
     commentators
    0.07
    abbrev
    0.07
     Nem
    0.07
     specialists
    0.07
    构造
    0.07
     frontier
    0.06
     fds
    0.06
    Act Density 0.003%

    No Known Activations