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

    Neuronpedia

    INDEX
    Explanations

    GGML/GGUF models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cot
    0.77
    oooo
    0.75
    oooooooo
    0.73
    ooo
    0.72
    kova
    0.70
    עות
    0.67
    ate
    0.66
    هُ
    0.63
    cn
    0.63
    erns
    0.62
    POSITIVE LOGITS
     fever
    0.77
     việc
    0.72
     định
    0.71
    这么
    0.70
     contempla
    0.69
    "",
    0.67
    olutely
    0.66
     tần
    0.66
     понимаю
    0.66
     рассказа
    0.66
    Act Density 0.001%

    No Known Activations