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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zien
    -0.06
    _STAT
    -0.06
     attn
    -0.06
     Ник
    -0.06
     maint
    -0.06
     ------------
    -0.06
    Txt
    -0.06
    �
    -0.06
     Nile
    -0.06
     Clem
    -0.06
    POSITIVE LOGITS
     severed
    0.07
    عت
    0.07
     resolution
    0.07
    ğında
    0.07
     символ
    0.07
    enção
    0.07
     o
    0.06
    Candidate
    0.06
     Resolution
    0.06
     equ
    0.06
    Act Density 0.001%

    No Known Activations