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

    Neuronpedia

    INDEX
    Explanations

    function notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Djibouti
    -0.52
    yadh
    -0.51
     Succ
    -0.51
     succ
    -0.50
     ninjas
    -0.48
    ASX
    -0.48
     one
    -0.48
     searches
    -0.47
    Salir
    -0.47
     minions
    -0.47
    POSITIVE LOGITS
     tartalomajánló
    0.78
     Италијани
    0.60
    UnusedPrivate
    0.60
    发表于
    0.53
     &___
    0.53
    Rüyada
    0.53
     виправивши
    0.52
     gärna
    0.52
    rungsseite
    0.52
    eradish
    0.51
    Act Density 0.040%

    No Known Activations