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

    Neuronpedia

    INDEX
    Explanations

    clusters of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     preparação
    0.65
    tidak
    0.65
     juga
    0.64
    alcoholic
    0.64
    Ketika
    0.59
     proveedor
    0.58
    ે
    0.58
     कराने
    0.58
     Leandro
    0.58
    场合
    0.58
    POSITIVE LOGITS
    들이
    0.76
    들의
    0.76
     encir
    0.73
    들은
    0.73
     clustered
    0.72
     forming
    0.70
     모양
    0.69
    holes
    0.68
    들
    0.67
    が集
    0.66
    Act Density 0.400%

    No Known Activations