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

    Neuronpedia

    INDEX
    Explanations

    x and y coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⛲
    0.68
     фестива
    0.67
    嬅
    0.66
    pinimg
    0.64
     Tjiwarl
    0.64
    themealdb
    0.64
    Hozzáférés
    0.64
    getRedTeam
    0.64
    Festival
    0.64
    segaretro
    0.63
    POSITIVE LOGITS
     vector
    0.93
     coefficients
    0.84
     x
    0.77
     components
    0.77
     vectors
    0.77
     component
    0.76
     coefficient
    0.73
    x
    0.73
     Vector
    0.72
    向量
    0.71
    Act Density 0.162%

    No Known Activations