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

    Neuronpedia

    INDEX
    Explanations

    Javascript keywords

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <style
    -0.07
     rho
    -0.07
    Titulo
    -0.07
     ягод
    -0.07
     Năm
    -0.07
    (fontSize
    -0.07
     pelo
    -0.06
    transition
    -0.06
     bout
    -0.06
    合作
    -0.06
    POSITIVE LOGITS
    tems
    0.06
    _collect
    0.06
     PRODUCTS
    0.06
     симв
    0.06
    ющая
    0.05
    +F
    0.05
     Scripture
    0.05
     ALOG
    0.05
     ignoring
    0.05
     Offensive
    0.05
    Act Density 0.024%

    No Known Activations