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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     represented
    -0.08
     rapidly
    -0.07
    뜬
    -0.07
     radians
    -0.07
    舞
    -0.07
    ationally
    -0.07
     Editor
    -0.07
     repeatedly
    -0.07
    QUIRED
    -0.07
     widely
    -0.06
    POSITIVE LOGITS
    медицинск
    0.07
    cts
    0.07
     connections
    0.07
     colonial
    0.07
     cheesy
    0.07
    合肥市
    0.06
    耇
    0.06
    .school
    0.06
    ()=>
    0.06
     Lös
    0.06
    Act Density 0.034%

    No Known Activations