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

    Neuronpedia

    INDEX
    Explanations

    non-natural language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sco
    -0.07
     Intelligent
    -0.07
     tot
    -0.06
     GENER
    -0.06
     publishers
    -0.06
     Lub
    -0.06
     faucet
    -0.06
     пацієн
    -0.06
     comprising
    -0.06
     approach
    -0.06
    POSITIVE LOGITS
     &&
↵
    0.06
    ارية
    0.06
    edula
    0.06
    @Xml
    0.06
    839
    0.06
    712
    0.06
    ,},↵
    0.06
    Inc
    0.06
    213
    0.06
     volum
    0.06
    Act Density 0.000%

    No Known Activations