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

    Neuronpedia

    INDEX
    Explanations

    support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sayesinde
    -0.08
     BAT
    -0.08
     Netflix
    -0.07
    Wikipedia
    -0.07
     /*↵
    -0.07
     (){↵
    -0.07
     Delf
    -0.07
     sonuc
    -0.07
     barr
    -0.07
     eest
    -0.07
    POSITIVE LOGITS
     ibyo
    0.10
    意思
    0.09
    观点
    0.09
     uro
    0.09
     appell
    0.08
     каждого
    0.08
     मुद्द
    0.08
     எண்ண
    0.08
     каждой
    0.08
     gemaakte
    0.08
    Act Density 0.025%

    No Known Activations