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

    Neuronpedia

    INDEX
    Explanations

    probabilistic, slow, update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     $<$
    0.40
     জ
    0.39
    ྥ
    0.38
     nh
    0.37
     \<
    0.37
     FBI
    0.37
     KGB
    0.37
     ആൻ
    0.37
    zana
    0.36
    Ꮙ
    0.36
    POSITIVE LOGITS
    Greater
    0.42
    enez
    0.41
    rint
    0.40
    Recall
    0.39
     agrand
    0.39
    ﹕
    0.39
    Transfer
    0.39
    войства
    0.39
    greater
    0.38
    Shi
    0.38
    Act Density 0.000%

    No Known Activations