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

    Neuronpedia

    INDEX
    Explanations

    /dev/null, /dev/urandom, dev tun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फे
    0.41
    नन
    0.39
     Ogni
    0.39
     फेक
    0.39
    ারক
    0.38
     ogni
    0.38
    רץ
    0.38
    arrière
    0.38
    意識
    0.37
    看法
    0.37
    POSITIVE LOGITS
    Dev
    1.02
     Dev
    0.96
     dev
    0.93
     DEV
    0.81
     Devon
    0.79
    dev
    0.77
     Devi
    0.73
    DEV
    0.70
     devad
    0.69
     DeV
    0.66
    Act Density 0.011%

    No Known Activations