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

    Neuronpedia

    INDEX
    Explanations

    functional requirements and test ids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     álgebra
    0.44
     başlam
    0.37
     riego
    0.36
     öner
    0.36
    রামর্শ
    0.35
     tenere
    0.35
     całej
    0.35
    eluk
    0.34
     Isabella
    0.34
    рованная
    0.34
    POSITIVE LOGITS
     「
    0.37
    ＜
    0.36
    （
    0.36
     用
    0.35
    「
    0.35
    ㅣ
    0.35
    (+)
    0.35
    酉
    0.35
    vora
    0.34
     capacitances
    0.34
    Act Density 0.002%

    No Known Activations