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

    Neuronpedia

    INDEX
    Explanations

    lists, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पुन्हा
    0.34
     цель
    0.34
    ಚಿತ
    0.33
     仕様
    0.33
    సూరు
    0.32
     repeatability
    0.32
     grasses
    0.32
     paltry
    0.32
     ఎవ
    0.31
     outstretched
    0.31
    POSITIVE LOGITS
    などの
    0.56
     etc
    0.51
    など
    0.47
    etc
    0.46
     valamint
    0.46
     وغیرہ
    0.44
     тощо
    0.43
    ↵
    0.43
    なども
    0.41
    などが
    0.40
    Act Density 0.036%

    No Known Activations