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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     densely
    -0.06
     "+"
    -0.06
    _saved
    -0.06
     сох
    -0.06
    中学
    -0.06
    atoms
    -0.06
     sweat
    -0.06
    _scheduler
    -0.06
    rodu
    -0.06
    Regions
    -0.06
    POSITIVE LOGITS
     Interface
    0.06
     Schl
    0.06
    _bug
    0.06
    Normals
    0.06
     LTC
    0.06
    preneur
    0.06
     brig
    0.06
     REGARD
    0.06
     Phú
    0.06
     eclips
    0.06
    Act Density 0.041%

    No Known Activations