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

    Neuronpedia

    INDEX
    Explanations

    Bel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Aurora
    -0.08
    .endDate
    -0.07
     đông
    -0.07
     Reed
    -0.07
     Вік
    -0.07
     dışı
    -0.07
     pie
    -0.07
     rho
    -0.07
    Dies
    -0.06
    rieving
    -0.06
    POSITIVE LOGITS
     bel
    0.08
     Bel
    0.07
    Bel
    0.07
     Belly
    0.07
     BEL
    0.07
    Philadelphia
    0.07
    ब
    0.06
     والد
    0.06
     midst
    0.06
    علام
    0.06
    Act Density 0.012%

    No Known Activations