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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	load
    -0.08
    	vo
    -0.08
    <li
    -0.08
    Cookies
    -0.08
     Liqu
    -0.08
     COVID
    -0.08
     mise
    -0.07
    Comm
    -0.07
     schedule
    -0.07
     communal
    -0.07
    POSITIVE LOGITS
     gusto
    0.07
    팼
    0.07
    نصر
    0.07
     �
    0.06
    Ṫ
    0.06
    ehr
    0.06
    ELY
    0.06
    taş
    0.06
     defends
    0.06
    评测
    0.06
    Act Density 0.312%

    No Known Activations