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

    Neuronpedia

    INDEX
    Explanations

    secret societies and elopements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    접
    0.57
    วล
    0.54
    ่อย
    0.47
     ampl
    0.46
    וב
    0.46
    Businesses
    0.46
    طلح
    0.46
    ς
    0.45
     amph
    0.45
    Our
    0.45
    POSITIVE LOGITS
     ulcerative
    0.60
    gies
    0.55
    gender
    0.52
    йович
    0.50
     Matte
    0.50
    an
    0.49
    stato
    0.48
    rau
    0.48
    g
    0.47
    cione
    0.47
    Act Density 0.000%

    No Known Activations