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

    Neuronpedia

    INDEX
    Explanations

    Code, line numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Memphis
    -0.07
     contradict
    -0.07
    ennes
    -0.06
     Wu
    -0.06
     control
    -0.06
     priority
    -0.06
    ertia
    -0.06
     postal
    -0.06
     Env
    -0.06
    òa
    -0.06
    POSITIVE LOGITS
    .error
    0.07
     eSports
    0.06
    ');↵↵
    0.06
     Embed
    0.06
    pson
    0.06
     уровень
    0.06
    іблі
    0.06
    ,:),
    0.06
    泛
    0.06
     댓글
    0.06
    Act Density 0.229%

    No Known Activations