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

    Neuronpedia

    INDEX
    Explanations

    implied or not stated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     behaviors
    0.49
     perilaku
    0.47
     atypical
    0.46
     comportamenti
    0.46
     berkualitas
    0.44
     nedeniyle
    0.43
     crackdown
    0.43
    PLATES
    0.43
     kisah
    0.42
     straordin
    0.41
    POSITIVE LOGITS
     centre
    0.51
     cả
    0.48
     Cái
    0.47
     všech
    0.46
    óry
    0.45
     rightly
    0.44
    วจ
    0.44
    fw
    0.44
    łada
    0.43
     both
    0.43
    Act Density 0.020%

    No Known Activations