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

    Neuronpedia

    INDEX
    Explanations

    terrible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cancel
    -0.07
     hala
    -0.07
    ORE
    -0.07
     بازیگر
    -0.07
    handles
    -0.06
     arttır
    -0.06
     DAR
    -0.06
     směrem
    -0.06
     {};
    -0.06
     اول
    -0.06
    POSITIVE LOGITS
    صح
    0.07
     Appendix
    0.07
     kişisel
    0.06
    耐
    0.06
    .usage
    0.06
     baff
    0.06
    guard
    0.06
    HB
    0.06
    stat
    0.06
     ﾊ
    0.06
    Act Density 0.000%

    No Known Activations