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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    情的
    0.38
    Schwe
    0.35
    Toolkit
    0.35
    InputBorder
    0.34
     फलस्वरूप
    0.34
    Spacer
    0.34
    лій
    0.33
    <0x9B>
    0.32
     earliest
    0.32
    Eds
    0.32
    POSITIVE LOGITS
     sixty
    0.68
     eight
    0.68
     साढ़े
    0.66
     nine
    0.65
     twelve
    0.65
     zwölf
    0.65
     seven
    0.64
     six
    0.63
     thirteen
    0.63
    0.63
    Act Density 0.141%

    No Known Activations