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

    Neuronpedia

    INDEX
    Explanations

    realised

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .libs
    -0.07
     Brotherhood
    -0.07
    ARGS
    -0.06
    (AT
    -0.06
     внутріш
    -0.06
    SCII
    -0.06
    Naz
    -0.06
     Saints
    -0.06
    CurrentValue
    -0.06
    ('?
    -0.06
    POSITIVE LOGITS
     travellers
    0.08
     slag
    0.07
     ubiqu
    0.06
    ulares
    0.06
     pretend
    0.06
    aseline
    0.06
     pretending
    0.06
     орг
    0.06
    ishop
    0.06
     行
    0.06
    Act Density 0.041%

    No Known Activations