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

    Neuronpedia

    INDEX
    Explanations

    say births

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentState
    -0.07
     совсем
    -0.07
    ;/*
    -0.06
    ，以
    -0.06
     Так
    -0.06
    /hooks
    -0.06
    _watch
    -0.06
     sailors
    -0.06
     Associates
    -0.06
     Election
    -0.06
    POSITIVE LOGITS
    )]
↵
    0.07
    처
    0.07
    tele
    0.07
     massacre
    0.06
    νο
    0.06
     фін
    0.06
    τ
    0.06
     cruis
    0.06
     المل
    0.06
     forCell
    0.06
    Act Density 0.002%

    No Known Activations