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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LO
    -0.06
    T
    -0.06
     Tyr
    -0.06
     Lazar
    -0.06
    Isl
    -0.06
    -T
    -0.06
    Лю
    -0.06
     Rudd
    -0.06
    Fair
    -0.06
    _ignore
    -0.06
    POSITIVE LOGITS
     свое
    0.06
     کیل
    0.06
     envelope
    0.06
    .visitInsn
    0.06
    .espresso
    0.06
    .obj
    0.06
    085
    0.06
     itemprop
    0.06
     werde
    0.06
     multiplied
    0.06
    Act Density 0.035%

    No Known Activations