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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vznik
    -0.07
     severe
    -0.07
     neurons
    -0.07
    『
    -0.07
    subj
    -0.07
     mL
    -0.06
     vein
    -0.06
     every
    -0.06
    дут
    -0.06
     candles
    -0.06
    POSITIVE LOGITS
    ='%
    0.07
    Nuevo
    0.07
    (sig
    0.06
    0.06
    -President
    0.06
     редак
    0.06
    meye
    0.06
     potatoes
    0.06
     Riot
    0.06
     Ryzen
    0.06
    Act Density 0.024%

    No Known Activations