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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Defaults
    -0.09
    calculator
    -0.08
    Defaults
    -0.08
    tribution
    -0.08
    .vstack
    -0.08
    chapter
    -0.08
    <script
    -0.07
    defaults
    -0.07
    ücher
    -0.07
    _buffers
    -0.07
    POSITIVE LOGITS
     responses
    0.11
    (outputs
    0.10
    反馈
    0.09
     replies
    0.09
     reveals
    0.09
     informative
    0.09
    回应
    0.09
     outputs
    0.09
     Responses
    0.09
    リア
    0.08
    Act Density 0.010%

    No Known Activations