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

    Neuronpedia

    INDEX
    Explanations

    "ça va?" or "it came"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    believe
    0.47
    prising
    0.44
    laublich
    0.42
     hermaph
    0.42
    MatContext
    0.41
     sicherlich
    0.41
     अवश्य
    0.41
     dubbio
    0.40
    dwyd
    0.40
     vuccati
    0.40
    POSITIVE LOGITS
    ariously
    0.39
     Land
    0.38
    ’
    0.37
     rec
    0.37
     Labs
    0.37
    stalk
    0.35
     Des
    0.35
     എന്നി
    0.35
     des
    0.35
    が好き
    0.34
    Act Density 0.001%

    No Known Activations