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

    Neuronpedia

    INDEX
    Explanations

    heroes and praise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XF
    -0.07
    амп
    -0.07
     rus
    -0.07
    .learning
    -0.06
     ()↵
    -0.06
     EDT
    -0.06
     Arch
    -0.06
    xz
    -0.06
     "~
    -0.06
     комплек
    -0.06
    POSITIVE LOGITS
    uellement
    0.06
     theology
    0.06
    ических
    0.06
    aload
    0.06
     indices
    0.06
    .hpp
    0.06
    čný
    0.06
    osition
    0.06
     comeback
    0.06
    ++){
    0.06
    Act Density 0.060%

    No Known Activations