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

    Neuronpedia

    INDEX
    Explanations

    BuilderFactory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weise
    -0.07
     уровне
    -0.07
    creenshot
    -0.06
    ableView
    -0.06
    izione
    -0.06
     scripted
    -0.06
    átu
    -0.06
     cores
    -0.06
    InInspector
    -0.06
     Pence
    -0.06
    POSITIVE LOGITS
    _DESTROY
    0.07
     weddings
    0.06
    dist
    0.06
     swinging
    0.06
    Waiting
    0.06
    _down
    0.06
     ни
    0.06
    有
    0.06
     Ivan
    0.06
    anything
    0.06
    Act Density 0.000%

    No Known Activations