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

    Neuronpedia

    INDEX
    Explanations

    positioning/location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مرات
    -0.07
     Vám
    -0.07
     منت
    -0.07
     binary
    -0.06
     vanilla
    -0.06
     Quality
    -0.06
     south
    -0.06
    _NONE
    -0.06
     основ
    -0.06
     Save
    -0.06
    POSITIVE LOGITS
     locker
    0.07
     position
    0.07
    levelname
    0.06
     стоит
    0.06
    Dom
    0.06
    .Required
    0.06
    :set
    0.06
    0.06
    observation
    0.06
    0.06
    Act Density 0.004%

    No Known Activations