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

    Neuronpedia

    INDEX
    Explanations

    Effort/Force (various languages)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nobel
    -0.06
    ../../
    -0.06
     norms
    -0.06
     pioneers
    -0.06
     larvae
    -0.06
     tsunami
    -0.06
     enabling
    -0.06
     Sed
    -0.06
     built
    -0.06
     seo
    -0.06
    POSITIVE LOGITS
    ude
    0.07
    	Result
    0.07
     doz
    0.07
     WOM
    0.07
    ствия
    0.07
    Domin
    0.06
     thuốc
    0.06
    stream
    0.06
    든
    0.06
    forc
    0.06
    Act Density 0.003%

    No Known Activations