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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blind
    -0.07
     �
    -0.06
     대해
    -0.06
    슨
    -0.06
    /open
    -0.06
     Parsons
    -0.06
    (shared
    -0.06
     basketball
    -0.06
    ('${
    -0.06
     intimidation
    -0.06
    POSITIVE LOGITS
    .styleable
    0.07
    irical
    0.07
     oyn
    0.06
    _play
    0.06
     Và
    0.06
    IEEE
    0.06
    ognito
    0.06
    ンツ
    0.06
     örg
    0.06
    _DIP
    0.06
    Act Density 0.006%

    No Known Activations