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

    Neuronpedia

    INDEX
    Explanations

    Scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -comp
    -0.07
    ENTE
    -0.07
    מוג
    -0.07
    legt
    -0.07
     tù
    -0.07
     withdrawing
    -0.07
    ⬛
    -0.07
    efully
    -0.07
    Serve
    -0.06
    ért
    -0.06
    POSITIVE LOGITS
     Республик
    0.07
    });↵
    0.07
    ผ
    0.07
    (View
    0.07
    (pair
    0.07
    -Ass
    0.07
     located
    0.07
     Remember
    0.07
    (prediction
    0.07
    aper
    0.06
    Act Density 0.022%

    No Known Activations