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

    Neuronpedia

    INDEX
    Explanations

    listing categories and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    roskop
    0.39
    strncpy
    0.38
    jang
    0.37
     smiling
    0.37
     човек
    0.37
    朝着
    0.37
     abrog
    0.37
    ുമ്പോൾ
    0.36
    rman
    0.36
    achio
    0.36
    POSITIVE LOGITS
    Стра
    0.45
    بة
    0.40
    黍
    0.38
    စာ
    0.37
    性質
    0.37
     Schema
    0.37
    Укра
    0.37
    Ⲥ
    0.37
    ἃ
    0.37
    ಲೆ
    0.36
    Act Density 0.000%

    No Known Activations