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

    Neuronpedia

    INDEX
    Explanations

    job interview

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    water
    0.36
    message
    0.35
    layout
    0.35
    HTMLElement
    0.35
    color
    0.34
    symbol
    0.34
    lena
    0.34
    odt
    0.33
    springframework
    0.33
    histogram
    0.33
    POSITIVE LOGITS
     و
    0.36
     یا
    0.36
    和服务
    0.34
    และการ
    0.33
     complejidad
    0.32
    /
    0.32
     والأ
    0.32
     కానీ
    0.31
     évent
    0.31
     كور
    0.31
    Act Density 3.851%

    No Known Activations