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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abelle
    -0.09
    -awareness
    -0.08
    _behavior
    -0.08
     DUT
    -0.08
     Montessori
    -0.08
     han
    -0.08
     Awake
    -0.07
    -online
    -0.07
     workshop
    -0.07
    -worth
    -0.07
    POSITIVE LOGITS
     reservado
    0.08
     இதில்
    0.08
     bottled
    0.08
     događ
    0.08
     онда
    0.07
    汁
    0.07
     Doug
    0.07
     hardy
    0.07
    ಾನು
    0.07
     voorraad
    0.07
    Act Density 0.027%

    No Known Activations