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

    Neuronpedia

    INDEX
    Explanations

    visibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     composite
    -0.07
    าบ
    -0.07
     Vám
    -0.06
    ázi
    -0.06
     polis
    -0.06
    ("(%
    -0.06
     '_'
    -0.06
    (">
    -0.06
    twenty
    -0.06
    ὐ
    -0.06
    POSITIVE LOGITS
     Staten
    0.07
     उम
    0.06
    まで
    0.06
    適用
    0.06
     discussions
    0.06
     Miguel
    0.06
     warnings
    0.06
    -toggler
    0.06
    _tim
    0.06
     malaria
    0.06
    Act Density 0.046%

    No Known Activations