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

    Neuronpedia

    INDEX
    Explanations

    effort levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tochy
    0.46
     नवीनतम
    0.42
     वगैरह
    0.41
    🚜
    0.41
    enuine
    0.41
    <unused649>
    0.41
    issionais
    0.40
    ufieurs
    0.40
    >\<^
    0.39
    tsConfig
    0.39
    POSITIVE LOGITS
     both
    0.49
     skill
    0.43
     moderately
    0.41
     board
    0.41
     si
    0.40
     Mad
    0.39
     Alexander
    0.38
     psych
    0.38
     zowel
    0.38
     decis
    0.37
    Act Density 0.256%

    No Known Activations