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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SHOW
    -0.07
     userManager
    -0.07
    sanitize
    -0.07
    YYY
    -0.06
     lighting
    -0.06
    (scores
    -0.06
     secondo
    -0.06
    undance
    -0.06
    _dt
    -0.06
    	using
    -0.06
    POSITIVE LOGITS
     сах
    0.06
    :s
    0.06
     修
    0.06
     strav
    0.06
    (fabs
    0.06
     vc
    0.06
    redients
    0.06
    ตอน
    0.06
    �新
    0.06
    .btnClose
    0.06
    Act Density 0.070%

    No Known Activations