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

    Neuronpedia

    INDEX
    Explanations

    parsing text formats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iang
    -0.07
     Phot
    -0.07
     humor
    -0.07
     getClass
    -0.06
    arlar
    -0.06
    .connections
    -0.06
     helium
    -0.06
    illustr
    -0.06
    dělen
    -0.06
    clicked
    -0.06
    POSITIVE LOGITS
    contest
    0.06
     PAT
    0.06
    利
    0.06
    \xe
    0.06
    .email
    0.06
     Başkan
    0.05
    TT
    0.05
    vod
    0.05
    	puts
    0.05
    ･･
    0.05
    Act Density 0.093%

    No Known Activations