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

    Neuronpedia

    INDEX
    Explanations

    directly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     haus
    -0.08
    Town
    -0.08
    出院
    -0.07
    更
    -0.07
    ([],
    -0.07
    ([...
    -0.07
    unbind
    -0.07
    .RegisterType
    -0.07
    .parent
    -0.07
    城管
    -0.07
    POSITIVE LOGITS
    翯
    0.08
    딸
    0.08
    𠳐
    0.08
     individual
    0.07
    hands
    0.07
    岊
    0.07
    สามาร
    0.07
    藦
    0.06
    𝔴
    0.06
     Veronica
    0.06
    Act Density 0.022%

    No Known Activations