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

    Neuronpedia

    INDEX
    Explanations

    defer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    社會
    -0.07
     ||
    -0.07
    할
    -0.07
     Rakou
    -0.07
    操
    -0.07
    eket
    -0.06
    生命
    -0.06
    πε
    -0.06
    _TWO
    -0.06
    隨
    -0.06
    POSITIVE LOGITS
    .tasks
    0.07
     Rails
    0.07
    complete
    0.07
     Za
    0.06
     Betty
    0.06
    мів
    0.06
     youngster
    0.06
     decrypted
    0.06
    cams
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations