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

    Neuronpedia

    INDEX
    Explanations

    #include statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    camb
    -0.75
    cheap
    -0.73
    gradu
    -0.72
    druk
    -0.70
    ძ
    -0.68
    vegas
    -0.68
     Regents
    -0.67
    information
    -0.66
    ✯
    -0.65
    Beschrijving
    -0.65
    POSITIVE LOGITS
     يف
    0.72
    HRESULT
    0.71
    _("
    0.69
     eliminate
    0.68
     urea
    0.68
    curities
    0.68
    きん
    0.66
     dầu
    0.66
     مون
    0.66
     eliminated
    0.65
    Act Density 0.066%

    No Known Activations