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

    Neuronpedia

    INDEX
    Explanations

    indicators, impacts, states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drogas
    0.54
     vape
    0.53
    ни
    0.52
     obstante
    0.52
    in
    0.48
    addElement
    0.47
    ্লেখ
    0.46
    например
    0.46
    ਲਾਂ
    0.46
     que
    0.46
    POSITIVE LOGITS
    党委
    0.53
     Contracts
    0.46
     די
    0.45
    をつ
    0.45
    @
    0.44
     обяза
    0.43
     seams
    0.43
    菉
    0.43
    其實
    0.42
     عزت
    0.42
    Act Density 0.000%

    No Known Activations