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

    Neuronpedia

    INDEX
    Explanations

    apt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     East
    -0.07
    who
    -0.07
    (String
    -0.06
    뱀
    -0.06
    itian
    -0.06
     Butterfly
    -0.06
    打通
    -0.06
    urrenc
    -0.06
     Daemon
    -0.06
     Springfield
    -0.06
    POSITIVE LOGITS
     używa
    0.08
    謂
    0.07
    矢
    0.07
    )!↵
    0.07
    _RESOURCE
    0.07
    词语
    0.07
    .identity
    0.07
    极易
    0.07
    UB
    0.07
    갖
    0.07
    Act Density 0.003%

    No Known Activations