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

    Neuronpedia

    INDEX
    Explanations

    amp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    niejs
    -0.06
    Featured
    -0.06
    -elements
    -0.06
    ительный
    -0.06
    드는
    -0.06
    άλ
    -0.06
     Youth
    -0.06
     blev
    -0.06
    -0.06
    чних
    -0.06
    POSITIVE LOGITS
     म
    0.07
    FFE
    0.07
    �
    0.07
    .Dropout
    0.07
     прес
    0.06
     LAW
    0.06
    yecto
    0.06
     |=
    0.06
     Сан
    0.06
    .There
    0.06
    Act Density 0.001%

    No Known Activations