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

    Neuronpedia

    INDEX
    Explanations

    board

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ffiti
    -0.07
    ूम
    -0.07
     거
    -0.07
     راهنم
    -0.07
     Zu
    -0.07
     đối
    -0.06
    ूँ
    -0.06
    lator
    -0.06
     účet
    -0.06
    ixin
    -0.06
    POSITIVE LOGITS
    (delta
    0.06
     astronomy
    0.06
    #####
    0.06
    jobs
    0.06
    ),
    0.06
    dump
    0.06
     프랑스
    0.06
    ('
    0.06
     Wildlife
    0.06
    _marshall
    0.06
    Act Density 0.000%

    No Known Activations