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

    Neuronpedia

    INDEX
    Explanations

    do's and don'ts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.95
     created
    0.73
     [
    0.70
     is
    0.69
     ticket
    0.69
    i
    0.69
     alias
    0.68
     stade
    0.67
     announces
    0.66
    :
    0.66
    POSITIVE LOGITS
    us
    1.03
    and
    0.91
    ip
    0.91
    on
    0.89
    pipelines
    0.87
    HPLC
    0.85
    1
    0.85
    បញ្ចប់
    0.84
    _
    0.83
    ပြင်
    0.82
    Act Density 0.001%

    No Known Activations