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

    Neuronpedia

    INDEX
    Explanations

    file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sgem
    0.42
    incu
    0.40
    жу
    0.38
     मौका
    0.37
    ctomy
    0.37
    🧸
    0.36
    touchstart
    0.36
    OLOG
    0.36
    ancha
    0.35
    ೆಗೆ
    0.35
    POSITIVE LOGITS
    dev
    0.63
    usr
    0.60
    etc
    0.54
    home
    0.53
     home
    0.52
    tmp
    0.50
    mnt
    0.48
    var
    0.45
     dev
    0.42
    Users
    0.41
    Act Density 0.004%

    No Known Activations