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

    Neuronpedia

    INDEX
    Explanations

    existence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kansas
    -0.07
     channels
    -0.06
    aad
    -0.06
    enen
    -0.06
     jerk
    -0.06
     dün
    -0.06
    orte
    -0.06
     work
    -0.06
    _bonus
    -0.06
     Guatemala
    -0.06
    POSITIVE LOGITS
     çift
    0.07
    .writeFileSync
    0.06
    setItem
    0.06
     obvyk
    0.06
    ，都
    0.06
     barring
    0.06
    对方
    0.06
    explained
    0.06
    RESULT
    0.06
    择
    0.06
    Act Density 0.006%

    No Known Activations