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

    Neuronpedia

    INDEX
    Explanations

    codes with letters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeep
    0.47
    近平
    0.46
     joker
    0.45
    敚
    0.44
     Alfredo
    0.42
     enough
    0.40
     সমু
    0.39
     bilingual
    0.39
    ACITY
    0.39
     Shelley
    0.39
    POSITIVE LOGITS
    B
    0.50
    G
    0.47
    F
    0.46
    Н
    0.46
    ko
    0.44
     G
    0.43
    H
    0.43
    З
    0.43
     конструкции
    0.42
    Passive
    0.41
    Act Density 0.004%

    No Known Activations