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

    Neuronpedia

    INDEX
    Explanations

    before and after events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обстоя
    0.46
     ઘટના
    0.43
     adhipp
    0.41
     ditth
    0.39
    ढ़
    0.39
     dhammo
    0.38
     услы
    0.38
     MONITOR
    0.37
    efois
    0.37
    שׁ
    0.37
    POSITIVE LOGITS
    /
    0.46
    odel
    0.44
    iv
    0.43
    iser
    0.41
     &
    0.41
    ov
    0.41
    essere
    0.41
    first
    0.40
     rod
    0.40
    vas
    0.39
    Act Density 0.004%

    No Known Activations