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

    Neuronpedia

    INDEX
    Explanations

    technical programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miscon
    0.52
     leth
    0.50
     flaps
    0.48
    lerde
    0.48
    ęcie
    0.48
    in
    0.48
    inį
    0.47
    თვის
    0.47
     sequester
    0.47
     bluntly
    0.47
    POSITIVE LOGITS
    p
    0.54
    漀
    0.50
    terra
    0.49
    ALI
    0.48
    v
    0.48
    ARR
    0.46
    円以上
    0.46
    onne
    0.46
    وال
    0.45
    hrer
    0.45
    Act Density 0.000%

    No Known Activations