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

    Neuronpedia

    INDEX
    Explanations

    descriptive headings and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    es
    0.44
    मित्रा
    0.43
    ge
    0.43
    lden
    0.41
    eters
    0.40
    ai
    0.40
     hafa
    0.40
    elow
    0.40
     Vers
    0.39
    ך
    0.39
    POSITIVE LOGITS
     یک
    0.49
    )=(
    0.47
     توصیه
    0.46
     conviction
    0.46
    峹
    0.46
    크
    0.45
    懈
    0.45
    odoxy
    0.44
    subscribed
    0.44
     हाम्रो
    0.44
    Act Density 0.000%

    No Known Activations