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

    Neuronpedia

    INDEX
    Explanations

    discussions of what is missing or absent

    oai_token-act-pair · gemini-2.0-flash

    legal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     references
    -0.54
     Référence
    -0.52
     setValue
    -0.52
     REFERENCES
    -0.50
    rateful
    -0.49
    raszam
    -0.48
    Tē
    -0.48
    proy
    -0.48
    $\$$
    -0.47
    ραγ
    -0.47
    POSITIVE LOGITS
    Referències
    0.80
    Przypisy
    0.75
     EdgeInsets
    0.71
     estekak
    0.70
    AxisAlignment
    0.70
     חיצוניים
    0.69
     propOrder
    0.67
     Walkover
    0.67
     विश्वसनीयता
    0.67
    expandindo
    0.66
    Act Density 0.782%

    No Known Activations