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

    Neuronpedia

    INDEX
    Explanations

    axis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    细化
    -0.08
    .Http
    -0.07
    (Model
    -0.07
    nop
    -0.07
    .SystemColors
    -0.07
    若有
    -0.07
     elder
    -0.06
    โส
    -0.06
    埝
    -0.06
    🔃
    -0.06
    POSITIVE LOGITS
     axis
    0.08
    .temperature
    0.07
    acity
    0.07
    总投资
    0.07
    Ḵ
    0.07
    PEND
    0.07
    .axis
    0.07
    =Y
    0.06
    STRUCTIONS
    0.06
    Axis
    0.06
    Act Density 0.011%

    No Known Activations