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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ujících
    -0.07
    corn
    -0.06
     их
    -0.06
    quat
    -0.06
    udget
    -0.06
     fus
    -0.06
     Hen
    -0.06
    imps
    -0.06
    .shapes
    -0.06
     ¥
    -0.06
    POSITIVE LOGITS
    ])
    0.09
    """
    0.07
    จะได
    0.07
    firm
    0.07
     разви
    0.07
    >')
    0.06
     Claud
    0.06
    zsche
    0.06
    воб
    0.06
     {//
    0.06
    Act Density 0.002%

    No Known Activations