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

    Neuronpedia

    INDEX
    Explanations

    number of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InMemory
    0.51
    '
    0.51
    Online
    0.50
    cation
    0.50
    POV
    0.50
    Caption
    0.49
    text
    0.49
    street
    0.49
    seu
    0.47
    ಾದ
    0.46
    POSITIVE LOGITS
     hordes
    0.83
     människor
    0.82
     pessoas
    0.77
     sytuacji
    0.76
     ljudi
    0.71
     personer
    0.71
     mennesker
    0.69
     oameni
    0.69
     người
    0.68
     confrontations
    0.68
    Act Density 0.002%

    No Known Activations