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

    Neuronpedia

    INDEX
    Explanations

    Technical descriptions/patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     імен
    -0.07
     Venice
    -0.07
    ۷
    -0.06
     shout
    -0.06
     ">
    -0.06
    ICE
    -0.06
     logical
    -0.06
     veut
    -0.06
     clouds
    -0.06
     funny
    -0.06
    POSITIVE LOGITS
     thereafter
    0.08
     thereby
    0.08
    _he
    0.08
    by
    0.07
     thereof
    0.07
     обработ
    0.07
    pta
    0.07
    (#
    0.07
    .activate
    0.07
     By
    0.07
    Act Density 0.011%

    No Known Activations