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

    Neuronpedia

    INDEX
    Explanations

    about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dose
    0.41
     C
    0.40
     failure
    0.40
     Bar
    0.39
     Sche
    0.39
     Singh
    0.38
     Ku
    0.38
     villages
    0.38
     ability
    0.38
     Pip
    0.38
    POSITIVE LOGITS
    来店
    0.46
    .??.??"]
    0.45
     тексти
    0.45
    盎
    0.44
    ativen
    0.42
    echolog
    0.42
    缓
    0.42
     метал
    0.41
    挍
    0.41
     металли
    0.41
    Act Density 0.000%

    No Known Activations