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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幸福
    -0.07
    (ib
    -0.07
    єю
    -0.06
    μοί
    -0.06
    разд
    -0.06
    lobby
    -0.06
     витами
    -0.06
     以
    -0.06
    .correct
    -0.06
    ามารถ
    -0.06
    POSITIVE LOGITS
     cotton
    0.06
     dove
    0.06
    jad
    0.06
    .navigateTo
    0.06
     Solar
    0.06
    subplot
    0.06
    震
    0.06
    _permissions
    0.06
     louder
    0.06
     "+"
    0.06
    Act Density 0.002%

    No Known Activations