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

    Neuronpedia

    INDEX
    Explanations

    automated systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autopsy
    -0.08
     spying
    -0.07
    叹息
    -0.07
    宏大
    -0.07
    ervention
    -0.07
    vt
    -0.06
    (PHP
    -0.06
    轺
    -0.06
     sober
    -0.06
    海边
    -0.06
    POSITIVE LOGITS
     Mare
    0.07
     Filters
    0.07
    不来
    0.07
    界的
    0.07
    ⟫
    0.07
    .*
    0.07
    KS
    0.06
    年之久
    0.06
     사회
    0.06
    就得
    0.06
    Act Density 0.158%

    No Known Activations