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

    Neuronpedia

    INDEX
    Explanations

    .h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Component
    -0.08
    609
    -0.06
    _backup
    -0.06
     alf
    -0.06
     POST
    -0.06
     TRAIN
    -0.06
    (post
    -0.06
     territor
    -0.06
     appeal
    -0.06
     persu
    -0.06
    POSITIVE LOGITS
    .h
    0.08
    .hpp
    0.07
    そう
    0.07
     双
    0.06
    cerer
    0.06
    ひ
    0.06
     pierws
    0.06
    zeň
    0.06
    无码
    0.06
    underscore
    0.06
    Act Density 0.003%

    No Known Activations