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

    Neuronpedia

    INDEX
    Explanations

    font-weight CSS property

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contemplated
    1.33
    st
    1.26
    inetics
    1.23
    idade
    1.20
     selle
    1.20
    çamento
    1.18
    irthday
    1.17
    ल्पनिक
    1.15
    ize
    1.14
    iane
    1.13
    POSITIVE LOGITS
     highlights
    1.31
    აში
    1.19
     %>/
    1.18
     Appeals
    1.18
    ام
    1.18
     probabilities
    1.17
    ню
    1.16
    πλ
    1.15
    总部
    1.15
     그럼
    1.15
    Act Density 0.000%

    No Known Activations