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

    Neuronpedia

    INDEX
    Explanations

    Wikipedia page sections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mouse
    -0.06
    ogan
    -0.06
     Patient
    -0.06
    	Image
    -0.06
     recipient
    -0.06
    	dist
    -0.06
    ApiClient
    -0.06
     данных
    -0.06
    	Matrix
    -0.06
    arrera
    -0.06
    POSITIVE LOGITS
     абсолют
    0.07
     trou
    0.07
    	TokenName
    0.07
    实
    0.07
     сент
    0.06
    .Lang
    0.06
    -bodied
    0.06
     след
    0.06
    Ê
    0.06
    ensual
    0.06
    Act Density 0.005%

    No Known Activations