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

    Neuronpedia

    INDEX
    Explanations

    academic journals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NetAmount
    0.44
    htim
    0.43
     段
    0.43
     moduleId
    0.41
    可怕
    0.41
    শ্ত
    0.40
    ểu
    0.40
    hattim
    0.39
    نیم
    0.39
    recipe
    0.39
    POSITIVE LOGITS
     vol
    0.82
     journal
    0.81
     Vol
    0.79
     Journal
    0.76
    Vol
    0.69
    journal
    0.68
    Journal
    0.67
    ISSN
    0.64
    vol
    0.64
     Volume
    0.63
    Act Density 0.005%

    No Known Activations