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

    Neuronpedia

    INDEX
    Explanations

    due

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     placements
    -0.08
    n
    -0.07
    授
    -0.07
    ّ
    -0.07
    ยอด
    -0.06
    法人
    -0.06
     projekt
    -0.06
    $d
    -0.06
    N
    -0.06
     portfolios
    -0.06
    POSITIVE LOGITS
     Crimes
    0.07
    .ylim
    0.07
     WTF
    0.06
    ."[
    0.06
    _MUL
    0.06
    iphertext
    0.06
    ecake
    0.06
     DOES
    0.06
    .addAll
    0.06
    .surname
    0.06
    Act Density 0.001%

    No Known Activations