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

    Neuronpedia

    INDEX
    Explanations

    neural network code layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Publisher
    -0.07
    otts
    -0.06
    :x
    -0.06
    iệm
    -0.06
    ývá
    -0.06
     Unsure
    -0.06
     half
    -0.06
    忙
    -0.06
    ()',
    -0.06
    .sleep
    -0.05
    POSITIVE LOGITS
     gross
    0.08
     no
    0.06
     squeezed
    0.06
     nodded
    0.06
     orth
    0.06
     elimin
    0.06
    าหล
    0.06
    غراف
    0.06
    scar
    0.06
     غير
    0.06
    Act Density 0.029%

    No Known Activations