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

    Neuronpedia

    INDEX
    Explanations

    technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pumpkin
    -0.08
     Drum
    -0.08
    Mana
    -0.07
     renewal
    -0.07
     jumping
    -0.07
    Modules
    -0.07
    .views
    -0.07
     Stanton
    -0.07
     funcs
    -0.07
    签约
    -0.07
    POSITIVE LOGITS
    验
    0.08
    ikipedia
    0.07
     ulaş
    0.07
    ないと
    0.07
    坨
    0.07
     Explanation
    0.07
    黢
    0.06
    cı
    0.06
    icals
    0.06
    elfast
    0.06
    Act Density 0.246%

    No Known Activations