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

    Neuronpedia

    INDEX
    Explanations

    specific words and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Manufact
    0.49
    Consent
    0.45
     consent
    0.42
     nal
    0.40
     consentimiento
    0.39
     फ्रैक्शन
    0.39
     thỏa
    0.39
     тра
    0.38
     Mfg
    0.38
     Consent
    0.38
    POSITIVE LOGITS
     skipping
    0.37
    Pall
    0.36
     skip
    0.35
     Pall
    0.35
     scary
    0.34
    ದಾ
    0.34
    SKIP
    0.34
     Pa
    0.34
     blessed
    0.34
     Sanct
    0.34
    Act Density 0.001%

    No Known Activations