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

    Neuronpedia

    INDEX
    Explanations

    NB

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    יז
    -0.08
    롤
    -0.07
    pun
    -0.07
     Psychology
    -0.07
    釋
    -0.07
    释
    -0.07
    拉着
    -0.07
    customize
    -0.07
    ổ
    -0.07
    职
    -0.07
    POSITIVE LOGITS
     한번
    0.08
     диагност
    0.07
     רגל
    0.07
    🏋
    0.07
     {},
    0.07
    _RGCTX
    0.07
     Bucc
    0.06
    _nb
    0.06
     dequeueReusableCellWithIdentifier
    0.06
    יבה
    0.06
    Act Density 0.007%

    No Known Activations