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

    Neuronpedia

    INDEX
    Explanations

    writing prompts and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IVATE
    1.54
    داد
    1.42
    mies
    1.35
    тивно
    1.35
    itories
    1.34
     afterDir
    1.34
    jednoc
    1.32
     bureaucr
    1.28
    rison
    1.28
    ionante
    1.25
    POSITIVE LOGITS
     gama
    1.85
     variety
    1.80
     Range
    1.75
     net
    1.66
     Lage
    1.66
     lig
    1.64
     Angle
    1.64
     Had
    1.64
     Alt
    1.62
     온도
    1.60
    Act Density 0.051%

    No Known Activations