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

    Neuronpedia

    INDEX
    Explanations

    systems engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻝ
    1.83
     developments
    1.77
    ミュージ
    1.69
    ทางการ
    1.69
    ಿಗ
    1.68
    মা
    1.66
     peninsula
    1.66
     unsurprisingly
    1.65
     supremacist
    1.63
    шие
    1.63
    POSITIVE LOGITS
    ре
    2.44
    ל
    2.31
    daki
    2.30
    r
    2.30
    rt
    2.11
    rl
    2.09
    al
    2.08
    م
    2.08
    ifting
    2.03
    rat
    2.00
    Act Density 0.131%

    No Known Activations