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

    Neuronpedia

    INDEX
    Explanations

    git github repositories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forms
    2.00
     sockfd
    1.86
    ᑎ
    1.82
    textAllCaps
    1.79
     τά
    1.68
    ••••
    1.66
    bé
    1.65
    Forms
    1.64
    locationY
    1.64
    setClass
    1.64
    POSITIVE LOGITS
     قص
    1.89
    ्व
    1.83
    𝗮
    1.80
    𝗲
    1.80
    estown
    1.80
    𝘁
    1.75
     Short
    1.74
     />}
    1.73
     pik
    1.71
    ठमाड
    1.70
    Act Density 0.348%

    No Known Activations