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

    Neuronpedia

    INDEX
    Explanations

    source code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ecoin
    0.44
     व्यावसायिक
    0.41
     리그
    0.39
    andelions
    0.39
    लिप
    0.39
     आरामदायक
    0.39
     हाला
    0.38
    Letter
    0.38
     තම
    0.38
     ज़
    0.38
    POSITIVE LOGITS
    ソース
    0.41
    어가
    0.38
     அறிய
    0.38
     arranque
    0.37
    UOUS
    0.37
    INATION
    0.37
    工場
    0.36
     source
    0.35
    ДС
    0.35
    ચર
    0.35
    Act Density 0.000%

    No Known Activations