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

    Neuronpedia

    INDEX
    Explanations

    JSDoc comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lemek
    0.41
    జ్‌
    0.40
    вите
    0.39
     Lê
    0.39
     款
    0.38
     gradioApp
    0.38
     Zentral
    0.38
     పంట
    0.38
     Vodafone
    0.37
     स्पष्ट
    0.37
    POSITIVE LOGITS
    olds
    0.46
     slips
    0.42
    abilis
    0.40
     terrible
    0.37
     পরেও
    0.37
    Sne
    0.36
    atsii
    0.36
     slipping
    0.36
    东西
    0.35
    abilities
    0.35
    Act Density 0.003%

    No Known Activations