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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أم
    -0.07
    .Ass
    -0.07
     verifier
    -0.06
     urgent
    -0.06
    起来
    -0.06
    /false
    -0.06
    /source
    -0.06
     ($(
    -0.06
     平
    -0.06
     nắng
    -0.06
    POSITIVE LOGITS
    сю
    0.07
    егод
    0.06
     scenic
    0.06
    "]/
    0.06
    	mem
    0.06
    .panel
    0.06
     enters
    0.06
     Trev
    0.06
    _PERMISSION
    0.06
     versatility
    0.06
    Act Density 0.002%

    No Known Activations