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

    Neuronpedia

    INDEX
    Explanations

    Anthropic, anthropology, anthros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.31
    т
    1.20
    त
    1.02
    t
    0.98
    AA
    0.93
    د
    0.93
    ก
    0.93
    る
    0.93
    ES
    0.90
    ا
    0.88
    POSITIVE LOGITS
    <0x80>
    0.80
    '
    0.79
     in
    0.77
    ;
    0.77
    0.73
    in
    0.72
     judiciary
    0.68
     불구하고
    0.68
    0.66
     Philippine
    0.66
    Act Density 0.031%

    No Known Activations