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

    Neuronpedia

    INDEX
    Explanations

    pack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脑
    -0.09
     continuous
    -0.07
     nights
    -0.07
     Were
    -0.07
     fuera
    -0.06
     satellite
    -0.06
    ころ
    -0.06
     Idaho
    -0.06
    soever
    -0.06
     anche
    -0.06
    POSITIVE LOGITS
    标准
    0.08
    classic
    0.07
    -expand
    0.07
    -register
    0.07
    .ADD
    0.07
    _INSTALL
    0.07
    strate
    0.07
    cw
    0.07
    Ζ
    0.07
    .DEFAULT
    0.07
    Act Density 0.007%

    No Known Activations