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

    Neuronpedia

    INDEX
    Explanations

    grams per, lowercase letter, ketones, growth of, version of, virtual currencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    com
    0.53
    model
    0.50
    file
    0.47
    du
    0.47
    boot
    0.47
    http
    0.46
    modified
    0.46
    th
    0.45
    toilet
    0.44
    (
    0.44
    POSITIVE LOGITS
     se
    0.53
     lados
    0.49
     vì
    0.49
     vehement
    0.48
     ocorrer
    0.47
     serem
    0.47
     porque
    0.46
     mesons
    0.46
     být
    0.45
     so
    0.45
    Act Density 0.046%

    No Known Activations