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

    Neuronpedia

    INDEX
    Explanations

    less than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    relsen
    0.47
    🏋
    0.45
     मोटरसा
    0.44
     През
    0.44
    Blog
    0.44
    úncia
    0.44
    Incoming
    0.43
    фото
    0.43
    стре
    0.41
    ುಂಬ
    0.41
    POSITIVE LOGITS
    0.43
    abilir
    0.43
    withtag
    0.42
     Geneva
    0.41
     arab
    0.41
     يون
    0.40
     jj
    0.40
     éx
    0.39
     عند
    0.39
     anywhere
    0.39
    Act Density 0.000%

    No Known Activations