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

    Neuronpedia

    INDEX
    Explanations

    multiple opportunities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     американ
    0.47
     hz
    0.46
     разделить
    0.46
     đầy
    0.45
     ym
    0.43
     chur
    0.42
     сы
    0.42
     american
    0.41
     macht
    0.41
     entwick
    0.40
    POSITIVE LOGITS
    CDATA
    0.42
    Managed
    0.42
    entrant
    0.42
     uncontrollable
    0.42
    itched
    0.41
     wParam
    0.41
    Congrats
    0.40
     provocation
    0.40
    edDevice
    0.40
    ็ง
    0.39
    Act Density 0.003%

    No Known Activations