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

    Neuronpedia

    INDEX
    Explanations

    filler text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تنها
    -0.07
     deck
    -0.06
     duo
    -0.06
     curator
    -0.06
     jsou
    -0.06
    _PUS
    -0.06
    combined
    -0.06
    แหล
    -0.06
     kvinn
    -0.06
     "\""
    -0.05
    POSITIVE LOGITS
    _slots
    0.07
    (constants
    0.07
     معدن
    0.07
    ']/
    0.07
     diffuse
    0.06
    œ
    0.06
    .StoredProcedure
    0.06
     TempData
    0.06
    \Models
    0.06
     знаком
    0.06
    Act Density 0.000%

    No Known Activations