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

    Neuronpedia

    INDEX
    Explanations

    differences or alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.81
     templates
    -0.69
     signatures
    -0.66
     gloire
    -0.65
     designs
    -0.65
     queries
    -0.65
     resolutions
    -0.63
     volumes
    -0.62
     forms
    -0.62
     indexes
    -0.61
    POSITIVE LOGITS
     pouvoirs
    0.62
     kind
    0.61
     subplot
    0.60
     bienfaits
    0.60
     épaules
    0.60
     prochaines
    0.59
    قایناق‌لار
    0.59
     églises
    0.59
     storyline
    0.59
    migrationBuilder
    0.58
    Act Density 0.082%

    No Known Activations