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

    Neuronpedia

    INDEX
    Explanations

    provides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     качества
    -0.07
    пеки
    -0.07
    "label
    -0.07
     стратег
    -0.07
     ties
    -0.07
    -key
    -0.07
    γέν
    -0.07
     القانون
    -0.07
    手
    -0.07
    ему
    -0.07
    POSITIVE LOGITS
    ibraltar
    0.07
     providing
    0.07
     PROVIDED
    0.07
     retrieved
    0.07
     GAR
    0.06
    imulator
    0.06
    ensitivity
    0.06
    occan
    0.06
                                                    ↵
    0.06
    provided
    0.06
    Act Density 0.006%

    No Known Activations