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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    анного
    -0.08
     Wandel
    -0.07
     behandel
    -0.07
     Nouvelle
    -0.07
     Neil
    -0.07
     HAC
    -0.07
     Malcolm
    -0.07
    ението
    -0.07
     ultime
    -0.07
     Sass
    -0.07
    POSITIVE LOGITS
     nữa
    0.11
    racha
    0.08
    arty
    0.08
     epit
    0.07
    실
    0.07
    psy
    0.07
     пі
    0.07
    wards
    0.07
    履
    0.07
     만나
    0.07
    Act Density 0.026%

    No Known Activations