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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and connector words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (browser
    -0.06
    ("#
    -0.06
     mountain
    -0.06
    onenumber
    -0.06
    .Black
    -0.06
    -reg
    -0.06
    agini
    -0.06
    patrick
    -0.06
    .getTotal
    -0.06
    -0.06
    POSITIVE LOGITS
     Dec
    0.07
    steam
    0.07
    mmas
    0.06
     लड़क
    0.06
    _DE
    0.06
     paranoia
    0.06
    -too
    0.06
     Troll
    0.06
    심
    0.06
    	NdrFc
    0.06
    Act Density 0.251%

    No Known Activations