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

    Neuronpedia

    INDEX
    Explanations

    cost per month

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    setMaximum
    0.72
    又要
    0.69
    ścic
    0.67
     vmax
    0.67
     ප්ර
    0.66
    tus
    0.66
     সমাবে
    0.66
     আওয়ামীলীগের
    0.66
    ဟု
    0.66
    нюю
    0.64
    POSITIVE LOGITS
    J
    0.71
    一会儿
    0.54
    ద
    0.51
    j
    0.51
    _
    0.50
    H
    0.49
     leid
    0.49
    ాల్సిన
    0.48
     من
    0.48
     insults
    0.47
    Act Density 0.020%

    No Known Activations