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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     역시
    -0.07
     billion
    -0.07
    花
    -0.07
     BEFORE
    -0.07
     imposing
    -0.07
     Wochen
    -0.06
     Fox
    -0.06
    	java
    -0.06
     campus
    -0.06
     Forgot
    -0.06
    POSITIVE LOGITS
    _et
    0.06
     russe
    0.06
    ceso
    0.06
     základní
    0.06
    žení
    0.06
     є
    0.06
    olesale
    0.06
     enth
    0.06
    .process
    0.06
    Sys
    0.06
    Act Density 0.020%

    No Known Activations