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

    Neuronpedia

    INDEX
    Explanations

    legal disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.08
    ался
    -0.07
     deliveries
    -0.07
     slova
    -0.07
    ались
    -0.07
    �
    -0.07
     unidades
    -0.07
     ensured
    -0.06
    during
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     wikipedia
    0.06
     Youtube
    0.06
    wand
    0.06
    (Operation
    0.06
     Downs
    0.06
     Noir
    0.06
    кан
    0.06
     NOTIFY
    0.06
    -д
    0.06
    露
    0.06
    Act Density 0.000%

    No Known Activations