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

    Neuronpedia

    INDEX
    Explanations

    Polynomial division

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abilece
    -0.08
     emotionally
    -0.08
    ె
    -0.07
    -ja
    -0.07
    .datasource
    -0.07
     ::↵↵
    -0.07
     emotional
    -0.07
     venu
    -0.07
     forum
    -0.07
     Meetup
    -0.07
    POSITIVE LOGITS
     ലക്ഷ
    0.09
     लक्ष्य
    0.09
     iterative
    0.08
     menyer
    0.08
     തുടങ്ങ
    0.08
     quotient
    0.08
    目标
    0.08
    Subtract
    0.08
    target
    0.08
     losses
    0.08
    Act Density 0.013%

    No Known Activations