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

    Neuronpedia

    INDEX
    Explanations

    higher/lower

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ak
    1.88
    ALL
    1.52
    toggle
    1.50
     हालाँकि
    1.37
    AD
    1.36
     похоже
    1.35
    .
    1.32
    ní
    1.31
    d
    1.31
    ligo
    1.28
    POSITIVE LOGITS
    ς
    1.63
     expectancy
    1.55
     Highness
    1.50
     وعلى
    1.49
    кі
    1.47
    кре
    1.41
     temperat
    1.41
     earners
    1.41
    てください
    1.38
     interpol
    1.37
    Act Density 0.196%

    No Known Activations