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

    Neuronpedia

    INDEX
    Explanations

    weights and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wymien
    0.83
     immediatamente
    0.81
    mują
    0.80
    venture
    0.80
    𝗹
    0.78
    슘
    0.78
     interstitiis
    0.77
     Bhuv
    0.77
    nashvillehousing
    0.77
    𝙪
    0.77
    POSITIVE LOGITS
     ↑
    0.82
     olmaz
    0.75
     teor
    0.67
    どう
    0.66
    莼
    0.65
     ಆಯ್
    0.65
     get
    0.65
     играет
    0.65
     לו
    0.64
     zaten
    0.64
    Act Density 0.010%

    No Known Activations