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

    Neuronpedia

    INDEX
    Explanations

    Seeing reflection in mirror

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جات
    -0.07
    utils
    -0.06
    232
    -0.06
    +(
    -0.06
     offsets
    -0.06
     خواب
    -0.06
    unken
    -0.06
    多
    -0.06
     selbst
    -0.06
    OVE
    -0.06
    POSITIVE LOGITS
     århus
    0.07
     splits
    0.06
    &w
    0.06
    tolist
    0.06
    lasyon
    0.06
     instit
    0.06
     Spect
    0.06
     speed
    0.06
    /sidebar
    0.06
     horny
    0.06
    Act Density 0.015%

    No Known Activations