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

    Neuronpedia

    INDEX
    Explanations

    conversation starter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cumulative
    -0.09
     cumul
    -0.08
    Fore
    -0.07
     Julia
    -0.07
     niet
    -0.07
     culmin
    -0.07
     peak
    -0.07
     Rome
    -0.07
     Jesu
    -0.07
     culminating
    -0.07
    POSITIVE LOGITS
    -provoking
    0.11
     intrigued
    0.10
    ήτη
    0.09
     posed
    0.09
    .Question
    0.09
     interessantes
    0.09
    ेश्य
    0.09
     eyebrow
    0.09
    ’ident
    0.08
     질문
    0.08
    Act Density 0.020%

    No Known Activations