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

    Neuronpedia

    INDEX
    Explanations

    face masks and contraception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /
    0.52
     on
    0.50
    in
    0.49
     of
    0.48
     car
    0.48
     connection
    0.47
     Connection
    0.47
     Class
    0.46
    </h2>
    0.45
     W
    0.44
    POSITIVE LOGITS
     prefque
    0.56
    Ре
    0.50
     erbjud
    0.49
    م
    0.46
    Из
    0.46
     koncent
    0.45
    ဒီ
    0.45
    ዑ
    0.45
     tepung
    0.44
    стоит
    0.44
    Act Density 0.000%

    No Known Activations