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

    Neuronpedia

    INDEX
    Explanations

    Erotica

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (plot
    -0.07
    _ARR
    -0.07
    ================================================
    -0.06
    ΡΙ
    -0.06
    (system
    -0.06
    &,
    -0.06
    куп
    -0.06
    ウォ
    -0.06
    ぬ
    -0.06
    ("(%
    -0.06
    POSITIVE LOGITS
    erusform
    0.06
    )})
    0.06
     dilig
    0.06
     figur
    0.06
     McCl
    0.06
    ensation
    0.06
    .filters
    0.06
     Texas
    0.06
     Appalachian
    0.06
    ');?>"
    0.06
    Act Density 0.053%

    No Known Activations