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

    Neuronpedia

    INDEX
    Explanations

    Departure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chang
    -0.07
     Pai
    -0.07
     leans
    -0.07
     brun
    -0.06
     Shake
    -0.06
    xda
    -0.06
     sick
    -0.06
     bene
    -0.06
     reckon
    -0.06
     Ko
    -0.06
    POSITIVE LOGITS
    ."<
    0.07
    ("..
    0.06
    ponses
    0.06
    	method
    0.06
     بیمار
    0.06
    ERICAN
    0.06
    욕
    0.06
    WebResponse
    0.06
     FIXED
    0.06
     exhibition
    0.06
    Act Density 0.000%

    No Known Activations