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

    Neuronpedia

    INDEX
    Explanations

    overload

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REA
    -0.08
    Compiler
    -0.08
    ਕਾਰ
    -0.08
    idium
    -0.08
    ئة
    -0.07
    ובת
    -0.07
     Ard
    -0.07
     Kathleen
    -0.07
    ored
    -0.07
    ROOT
    -0.07
    POSITIVE LOGITS
     gradual
    0.10
     постеп
    0.10
     gradually
    0.09
     वाढ
    0.09
     adecu
    0.09
     steig
    0.09
     постепенно
    0.09
     incrementar
    0.09
     inevitable
    0.09
     incre
    0.09
    Act Density 0.003%

    No Known Activations