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

    Neuronpedia

    INDEX
    Explanations

    fossil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    립
    -0.07
     hã
    -0.07
    _Request
    -0.07
    354
    -0.06
    ско
    -0.06
    urgent
    -0.06
    "]);
    -0.06
    BUM
    -0.06
    Plain
    -0.06
    MEM
    -0.06
    POSITIVE LOGITS
     gathering
    0.07
     »,
    0.06
     credits
    0.06
     المس
    0.06
    _hat
    0.06
     alf
    0.06
     appeals
    0.06
    (elem
    0.06
    (image
    0.06
    '%(
    0.06
    Act Density 0.015%

    No Known Activations