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

    Neuronpedia

    INDEX
    Explanations

    Heat or fluid loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poisonous
    -0.07
    言葉
    -0.07
    Component
    -0.07
     一
    -0.07
     regulators
    -0.06
    evaluation
    -0.06
    =Y
    -0.06
     Grip
    -0.06
    .two
    -0.06
    (L
    -0.06
    POSITIVE LOGITS
     dap
    0.07
    ▲
    0.07
    SRC
    0.07
    :@{
    0.06
    松
    0.06
    342
    0.06
    rana
    0.06
    _fw
    0.06
     pimp
    0.06
    ippo
    0.06
    Act Density 0.065%

    No Known Activations