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

    Neuronpedia

    INDEX
    Explanations

    private package repositories and mirrors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parvec
    0.44
    搧
    0.44
     التد
    0.43
    Diagonal
    0.42
    択
    0.42
     Diagonal
    0.42
     пье
    0.42
     Chir
    0.41
    郃
    0.41
     piede
    0.40
    POSITIVE LOGITS
     repositories
    0.91
     repository
    0.85
    repositories
    0.80
     Repository
    0.78
     mirror
    0.77
    repository
    0.75
     mirrors
    0.75
    mirror
    0.73
     mirroring
    0.70
    proxy
    0.69
    Act Density 0.014%

    No Known Activations