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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elo
    -0.08
     धन
    -0.07
     характер
    -0.07
    	HAL
    -0.07
     jego
    -0.06
    〕
    -0.06
     SWT
    -0.06
     geile
    -0.06
     stagnant
    -0.06
     demonic
    -0.06
    POSITIVE LOGITS
     Matches
    0.07
    .cap
    0.07
    -download
    0.07
    icense
    0.07
     ㅇㅇ
    0.07
     gy
    0.07
     smartphones
    0.06
    =request
    0.06
    orgh
    0.06
    \Form
    0.06
    Act Density 0.007%

    No Known Activations