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

    Neuronpedia

    INDEX
    Explanations

    political legitimacy and pricing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    written
    0.50
     Written
    0.48
    op
    0.45
    e
    0.44
    ق
    0.44
    נ
    0.44
    y
    0.44
    একটি
    0.42
    올
    0.42
    Economic
    0.42
    POSITIVE LOGITS
    ága
    0.50
     けど
    0.47
    టీఎం
    0.47
    ]*
    0.46
     Hershey
    0.46
    स्पून
    0.44
    也都
    0.44
    🐎
    0.44
     thighs
    0.43
    ))))
    0.43
    Act Density 0.002%

    No Known Activations