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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вла
    -0.08
     rainy
    -0.07
     shores
    -0.07
    (controller
    -0.07
    ูต
    -0.07
     shared
    -0.06
    .Bus
    -0.06
     faced
    -0.06
     lifting
    -0.06
    .Valid
    -0.06
    POSITIVE LOGITS
    -channel
    0.07
    (patient
    0.07
     Jim
    0.06
     Antoine
    0.06
     değerli
    0.06
    冷
    0.06
    美
    0.06
    _job
    0.06
     구매
    0.06
    ###↵
    0.06
    Act Density 0.000%

    No Known Activations