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

    Neuronpedia

    INDEX
    Explanations

    important qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Clear
    0.40
     clear
    0.39
     clearTimeout
    0.37
    clear
    0.36
     Appropriate
    0.35
     requisite
    0.34
     വ്യക്ത
    0.34
    Clear
    0.33
    explicit
    0.32
    ตน
    0.32
    POSITIVE LOGITS
     surprising
    0.54
     surprisingly
    0.54
     tough
    0.52
     tougher
    0.50
     toughest
    0.48
     really
    0.46
     okay
    0.45
     tempting
    0.45
     REALLY
    0.44
     wirklich
    0.43
    Act Density 0.049%

    No Known Activations