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

    Neuronpedia

    INDEX
    Explanations

    using namespace std;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '
    0.87
     "
    0.87
     state
    0.86
     far
    0.85
     delicate
    0.85
     controversial
    0.83
     mount
    0.80
     username
    0.80
     UN
    0.79
     remains
    0.79
    POSITIVE LOGITS
     Adapun
    1.23
    ätzlich
    1.17
     عنہ
    1.16
    éricos
    1.15
    jedno
    1.15
    asă
    1.14
    geschossiges
    1.13
    odată
    1.12
     liczb
    1.12
    fordern
    1.11
    Act Density 0.000%

    No Known Activations