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

    Neuronpedia

    INDEX
    Explanations

    code block separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     currentState
    0.47
    ود
    0.44
    ور
    0.43
    ור
    0.43
    িকের
    0.43
    و
    0.42
     Org
    0.42
     Live
    0.41
     Lat
    0.41
     Sink
    0.41
    POSITIVE LOGITS
    their
    0.48
    lden
    0.45
    tellers
    0.45
    ernen
    0.43
     тобто
    0.43
    hnen
    0.43
    liel
    0.43
    :
    0.43
    ogenen
    0.42
    ierzchn
    0.42
    Act Density 0.152%

    No Known Activations