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

    Neuronpedia

    INDEX
    Explanations

    correct response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adı
    0.42
    0.41
     thác
    0.39
     olacak
    0.39
     prefixes
    0.39
     |=
    0.38
    Automation
    0.38
     litros
    0.38
     hacerlo
    0.37
    mals
    0.37
    POSITIVE LOGITS
    ieť
    0.60
    あい
    0.50
    ukiyoe
    0.49
     เหมือน
    0.46
    ljiv
    0.46
     ք
    0.46
    といえば
    0.46
    壴
    0.46
    㡴
    0.46
    OUSE
    0.45
    Act Density 0.001%

    No Known Activations