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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instruction
    -0.07
    ئت
    -0.07
    audit
    -0.07
    contrast
    -0.07
    RTOS
    -0.07
    着眼于
    -0.07
    ’h
    -0.06
    Contr
    -0.06
     distr
    -0.06
    för
    -0.06
    POSITIVE LOGITS
    \Traits
    0.08
     bras
    0.07
    加盟商
    0.07
    illin
    0.07
    测算
    0.07
    (↵↵
    0.06
    checksum
    0.06
    蚶
    0.06
     Crossing
    0.06
    Printf
    0.06
    Act Density 0.056%

    No Known Activations