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

    Neuronpedia

    INDEX
    Explanations

    benchmark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Accessories
    -0.08
    GetProperty
    -0.07
    ArrayList
    -0.07
     acidic
    -0.07
     içeri
    -0.07
    -files
    -0.07
    (factory
    -0.07
     Reggie
    -0.07
     Cree
    -0.07
     equations
    -0.07
    POSITIVE LOGITS
     benchmark
    0.07
    stag
    0.07
    часно
    0.07
    abilecek
    0.07
    κού
    0.07
     landmark
    0.07
    IRM
    0.07
     centroid
    0.07
         
    0.07
     基
    0.06
    Act Density 0.008%

    No Known Activations