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

    Neuronpedia

    INDEX
    Explanations

    function tells

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undertakings
    0.48
    রের
    0.45
     odors
    0.43
     offenses
    0.43
     воздействия
    0.40
     CORPER
    0.40
     വാഹന
    0.40
     componentWill
    0.39
    ้ง
    0.39
     `>=`,
    0.39
    POSITIVE LOGITS
    0.48
     Surgeon
    0.45
     bernama
    0.44
     soddis
    0.42
     hari
    0.42
    am
    0.41
    ஞ்ஞான
    0.41
     rup
    0.41
     جدید
    0.40
    s
    0.39
    Act Density 0.007%

    No Known Activations