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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Palmer
    -0.07
     mounts
    -0.07
     Wolverine
    -0.07
    -member
    -0.06
     огром
    -0.06
    	curr
    -0.06
     overall
    -0.06
    уючи
    -0.06
    .title
    -0.06
    console
    -0.06
    POSITIVE LOGITS
     giden
    0.07
    Sil
    0.06
    hood
    0.06
     indebted
    0.06
    ेण
    0.06
    ो
    0.06
    бот
    0.06
     lookahead
    0.06
    pecting
    0.06
     lvl
    0.06
    Act Density 0.001%

    No Known Activations