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

    Neuronpedia

    INDEX
    Explanations

    when you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nutzer
    0.46
     সন্ব
    0.41
    동안
    0.41
     felonies
    0.41
     UserController
    0.40
    حول
    0.40
    धनों
    0.40
     Gewalt
    0.40
     Hindus
    0.39
     Benutzer
    0.39
    POSITIVE LOGITS
    LO
    0.37
    ()],
    0.37
    inc
    0.36
    irea
    0.36
    றவு
    0.36
    IRE
    0.35
    warf
    0.35
    INC
    0.35
    йин
    0.35
    \.
    0.35
    Act Density 0.000%

    No Known Activations