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

    Neuronpedia

    INDEX
    Explanations

    any input or provided text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     n
    0.40
    หล
    0.40
    树
    0.39
     Los
    0.39
    resulting
    0.39
    و
    0.39
     resulting
    0.38
     phi
    0.38
    ो
    0.38
    列
    0.38
    POSITIVE LOGITS
    enting
    0.42
     μέρος
    0.41
    vykor
    0.38
    诒
    0.38
     евро
    0.38
    ર્ક
    0.37
    вної
    0.37
    ებში
    0.37
    ucose
    0.36
     χρόνο
    0.36
    Act Density 0.000%

    No Known Activations