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

    Neuronpedia

    INDEX
    Explanations

    avoid jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Minute
    0.71
    Ré
    0.71
    нта
    0.69
     завжди
    0.69
    കോ
    0.68
     חד
    0.68
    SafeArea
    0.67
     الموافق
    0.67
    SHOT
    0.65
    RENC
    0.64
    POSITIVE LOGITS
    root
    0.73
    u
    0.73
     bauen
    0.72
    worst
    0.70
     paham
    0.70
    向けの
    0.70
    ollowing
    0.70
    芑
    0.68
    ított
    0.67
    mongoUrl
    0.66
    Act Density 0.001%

    No Known Activations