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

    Neuronpedia

    INDEX
    Explanations

    nation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     splice
    -0.07
    krét
    -0.06
     vše
    -0.06
    tractive
    -0.06
    ๕
    -0.06
    佐
    -0.06
    aq
    -0.06
     summarize
    -0.06
     Ко
    -0.06
     смерть
    -0.06
    POSITIVE LOGITS
     pend
    0.07
     کند
    0.06
    (TEXT
    0.06
    _signed
    0.06
     continent
    0.06
     jub
    0.06
     diverted
    0.06
     Vec
    0.06
    _MASK
    0.06
    _PARTITION
    0.06
    Act Density 0.022%

    No Known Activations