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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FY
    -0.07
    ầng
    -0.06
    VILLE
    -0.06
    Power
    -0.06
    _tcp
    -0.06
    holes
    -0.06
    Kind
    -0.06
    -op
    -0.06
    �
    -0.06
     Alex
    -0.06
    POSITIVE LOGITS
     crystals
    0.07
    _nr
    0.07
     oct
    0.06
     aktif
    0.06
     subtitles
    0.06
    orgt
    0.06
     coupling
    0.06
     ""}↵
    0.06
     barber
    0.06
    รอบ
    0.06
    Act Density 0.013%

    No Known Activations