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

    Neuronpedia

    INDEX
    Explanations

    Law and technology articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    QUOTE
    -0.07
     redundant
    -0.07
     seem
    -0.07
     seems
    -0.06
    cline
    -0.06
    Sounds
    -0.06
     skepticism
    -0.06
     Opr
    -0.06
     appears
    -0.06
     mentioned
    -0.06
    POSITIVE LOGITS
    /re
    0.08
    olik
    0.07
    と思
    0.07
    교
    0.07
    agua
    0.06
     milieu
    0.06
    heimer
    0.06
    cook
    0.06
    ISO
    0.06
     mashed
    0.06
    Act Density 0.000%

    No Known Activations