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

    Neuronpedia

    INDEX
    Explanations

    plot lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     확
    -0.07
     Seiten
    -0.07
    enco
    -0.06
     Všech
    -0.06
     >
↵
    -0.06
     polarization
    -0.06
    Album
    -0.06
    픈
    -0.06
    -capital
    -0.06
    ovou
    -0.06
    POSITIVE LOGITS
     storyline
    0.10
     basically
    0.07
     insider
    0.06
     insane
    0.06
     UPLOAD
    0.06
     ห
    0.06
     Signed
    0.06
    .usage
    0.06
    เตอร
    0.06
    	user
    0.06
    Act Density 0.008%

    No Known Activations