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

    Neuronpedia

    INDEX
    Explanations

    serious consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     between
    0.52
     eyeing
    0.48
     that
    0.46
    between
    0.45
     only
    0.44
     Between
    0.43
     discovering
    0.42
     BETWEEN
    0.40
     getting
    0.40
     Trim
    0.40
    POSITIVE LOGITS
     primacy
    0.47
    ản
    0.43
    AndView
    0.43
    აწილ
    0.42
    ឿង
    0.42
    aborasi
    0.42
    шими
    0.41
     Bildung
    0.41
    鸮
    0.41
    вропей
    0.41
    Act Density 0.007%

    No Known Activations