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

    Neuronpedia

    INDEX
    Explanations

    gauge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     identifier
    -0.08
    飞
    -0.07
     esc
    -0.07
    抓获
    -0.07
    而
    -0.07
     Federation
    -0.07
    feeding
    -0.07
     naz
    -0.07
    打扮
    -0.07
    Ｎ
    -0.07
    POSITIVE LOGITS
     chciał
    0.07
    믹
    0.07
     Może
    0.07
    .today
    0.06
    azioni
    0.06
    הזד
    0.06
    😼
    0.06
    .targets
    0.06
    .setColumns
    0.06
    ovid
    0.06
    Act Density 0.051%

    No Known Activations