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

    Neuronpedia

    INDEX
    Explanations

    numbers and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.69
     (
    0.68
     .
    0.57
     on
    0.55
     or
    0.55
     view
    0.54
     with
    0.54
     see
    0.54
    querySelector
    0.52
     =
    0.52
    POSITIVE LOGITS
     volontà
    0.76
     📫
    0.70
     desirous
    0.69
     voluntad
    0.69
    䣫
    0.68
    Jeśli
    0.67
     beserta
    0.67
    軖
    0.66
     trueMap
    0.66
    ClrBit
    0.66
    Act Density 0.001%

    No Known Activations