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

    Neuronpedia

    INDEX
    Explanations

    valves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     δημιουργ
    -0.07
     Nano
    -0.06
     Lenin
    -0.06
    aden
    -0.06
     Corrections
    -0.06
     мік
    -0.06
     detox
    -0.06
     healed
    -0.06
    igit
    -0.06
     giver
    -0.06
    POSITIVE LOGITS
    Until
    0.07
     Rem
    0.07
     oluştur
    0.07
    非常
    0.07
    .Token
    0.07
     studying
    0.06
    くと
    0.06
    (_("
    0.06
    .rstrip
    0.06
     (~(
    0.06
    Act Density 0.015%

    No Known Activations