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

    Neuronpedia

    INDEX
    Explanations

    Relationships and family

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comprise
    -0.07
     امن
    -0.07
     κου
    -0.06
    ND
    -0.06
    memberOf
    -0.06
    DIV
    -0.06
    чески
    -0.06
     maliyet
    -0.06
     phẩm
    -0.06
    QPCP
    -0.06
    POSITIVE LOGITS
    eden
    0.07
     |_
    0.06
     jeden
    0.06
     mamm
    0.06
     died
    0.06
    _que
    0.06
    -we
    0.06
     vy
    0.06
     cumshot
    0.06
     tốt
    0.05
    Act Density 0.040%

    No Known Activations