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

    Neuronpedia

    INDEX
    Explanations

    code, data, variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     banana
    -0.07
     towing
    -0.07
    λη
    -0.06
    ,U
    -0.06
    sten
    -0.06
    ponge
    -0.06
    agon
    -0.06
    Pan
    -0.06
     gor
    -0.06
    warn
    -0.06
    POSITIVE LOGITS
     "")
    0.06
    وید
    0.06
    WebResponse
    0.06
    antically
    0.06
    ?),
    0.06
     🙂↵↵
    0.06
     '{}
    0.06
     Watts
    0.06
    erb
    0.06
     октября
    0.06
    Act Density 0.000%

    No Known Activations