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

    Neuronpedia

    INDEX
    Explanations

    convicted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surveyed
    -0.06
     rice
    -0.06
    (txt
    -0.06
    こそ
    -0.06
     loaf
    -0.06
     tasked
    -0.06
     curled
    -0.06
    _LCD
    -0.06
    ические
    -0.06
     elk
    -0.06
    POSITIVE LOGITS
    (attributes
    0.07
     声
    0.07
     άλ
    0.07
    IndexOf
    0.07
    (Sender
    0.07
     فیلم
    0.07
    ैक
    0.07
    getResult
    0.06
    .pair
    0.06
    วม
    0.06
    Act Density 0.015%

    No Known Activations