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

    Neuronpedia

    INDEX
    Explanations

    area size and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅲ
    0.49
    ioners
    0.48
     Settlements
    0.47
     andDevice
    0.46
    于是
    0.45
    ネート
    0.45
    帀
    0.45
    строва
    0.44
    шча
    0.44
     নাকের
    0.43
    POSITIVE LOGITS
     long
    0.50
     seeking
    0.46
     a
    0.46
     use
    0.46
     be
    0.46
     an
    0.45
     turn
    0.45
     fighting
    0.45
     the
    0.44
     re
    0.44
    Act Density 0.000%

    No Known Activations