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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .prot
    -0.07
     extras
    -0.06
     засоб
    -0.06
     thirteen
    -0.06
    :S
    -0.06
    /th
    -0.06
    web
    -0.06
    _click
    -0.06
     Prot
    -0.06
    )__
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     fuzzy
    0.06
     adversary
    0.06
     awesome
    0.06
    gle
    0.06
     ngăn
    0.06
    /grpc
    0.06
     medio
    0.06
    टर
    0.06
     wannonce
    0.06
    Act Density 0.005%

    No Known Activations