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

    Neuronpedia

    INDEX
    Explanations

    URLs, including http and https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YPE
    0.74
    Importance
    0.71
     CheckException
    0.71
    NaOMe
    0.70
    ΙΚ
    0.70
    కీయ
    0.70
    igueur
    0.68
    PPE
    0.68
    evším
    0.67
    柺
    0.67
    POSITIVE LOGITS
    github
    0.92
     of
    0.87
    localhost
    0.82
     oleks
    0.80
     localhost
    0.80
     github
    0.77
    m
    0.77
     would
    0.77
     I
    0.75
    instagram
    0.75
    Act Density 0.000%

    No Known Activations