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

    Neuronpedia

    INDEX
    Explanations

    file path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Increment
    1.02
    ()*
    0.76
    Decrement
    0.76
    increment
    0.74
    Helper
    0.74
    hashtag
    0.71
    ()+
    0.69
    File
    0.69
    *((
    0.66
    GreaterThan
    0.66
    POSITIVE LOGITS
     doctrinal
    0.77
     fitting
    0.76
     Insol
    0.76
     Someone
    0.73
     serius
    0.72
     cabinets
    0.72
     semblance
    0.72
     unfit
    0.72
     Cabinet
    0.71
     lunatic
    0.71
    Act Density 0.324%

    No Known Activations