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

    Neuronpedia

    INDEX
    Explanations

    -v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sele
    -0.06
     attractive
    -0.06
     Bowen
    -0.06
    _ma
    -0.06
     квар
    -0.06
     spolupráci
    -0.06
     ویژگی
    -0.06
    遇
    -0.06
     Fool
    -0.06
     yorum
    -0.06
    POSITIVE LOGITS
     shrine
    0.07
    egie
    0.06
    ersed
    0.06
    _cats
    0.06
    oklyn
    0.06
    цять
    0.06
     عق
    0.06
    ERENCE
    0.06
    inqu
    0.06
     Carnegie
    0.06
    Act Density 0.000%

    No Known Activations