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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '[
    0.73
     `{
    0.70
     '['
    0.69
     Primary
    0.69
     стали
    0.69
     “(
    0.68
    ('['
    0.67
     पहल
    0.67
     “[
    0.67
     "["
    0.67
    POSITIVE LOGITS
    ./
    2.31
    }/
    2.12
    )/
    2.12
     ./
    2.11
    ]/
    1.96
    }}/
    1.95
     "./
    1.92
    "./
    1.92
     "/
    1.85
    +"/
    1.85
    Act Density 0.097%

    No Known Activations