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

    Neuronpedia

    INDEX
    Explanations

    Ubuntu PPA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deflate
    -0.80
     Polres
    -0.73
    acağ
    -0.73
     неодно
    -0.72
     valg
    -0.72
    onSave
    -0.72
     admins
    -0.71
    жды
    -0.71
    Lama
    -0.71
    produtos
    -0.70
    POSITIVE LOGITS
     Ubuntu
    1.09
    ubuntu
    0.90
     ju
    0.89
    Ubuntu
    0.87
     confinement
    0.86
     relation
    0.84
    ju
    0.83
    finement
    0.82
     series
    0.80
     conjure
    0.80
    Act Density 0.068%

    No Known Activations