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

    Neuronpedia

    INDEX
    Explanations

    invitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ungal
    -0.07
     לילדים
    -0.07
    糁
    -0.07
    vote
    -0.07
     tantra
    -0.07
    껴
    -0.07
    Advice
    -0.07
     normally
    -0.07
    agne
    -0.06
    都不会
    -0.06
    POSITIVE LOGITS
     IPv
    0.07
     SQ
    0.07
    _RSA
    0.07
    𓏧
    0.07
     כגון
    0.07
    ２
    0.07
    戴着
    0.07
     skew
    0.06
     Enterprise
    0.06
     Однако
    0.06
    Act Density 0.011%

    No Known Activations