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

    Neuronpedia

    INDEX
    Explanations

    specific item details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    referenced
    0.45
     منذ
    0.40
    lya
    0.39
    source
    0.39
     ໜອງ
    0.38
    ိုက်
    0.38
     玉
    0.38
    čak
    0.38
    玉
    0.38
     ზე
    0.37
    POSITIVE LOGITS
     COMMAND
    0.39
     '';
    0.37
     spins
    0.37
     proviso
    0.37
     plans
    0.37
     slic
    0.36
     PLANS
    0.36
     "";
    0.36
     ساخته
    0.36
     Halt
    0.36
    Act Density 0.000%

    No Known Activations