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

    Neuronpedia

    INDEX
    Explanations

    reflecting or growing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ფილი
    0.42
    欖
    0.42
    㭋
    0.41
     ethos
    0.41
    榄
    0.41
    緍
    0.40
    ﺯ
    0.40
    𝙜
    0.40
     tecnica
    0.40
    または
    0.39
    POSITIVE LOGITS
    -
    0.46
    ij
    0.45
     Growing
    0.43
     Moran
    0.43
    >\
    0.42
     Grow
    0.41
     Quan
    0.38
     grow
    0.38
    >-
    0.38
    ன்களை
    0.38
    Act Density 0.000%

    No Known Activations