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

    Neuronpedia

    INDEX
    Explanations

    collection of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     awards
    0.57
    awards
    0.52
     Award
    0.51
    Awards
    0.51
     award
    0.50
    award
    0.49
     पुरस्कार
    0.46
     awarded
    0.45
     Awards
    0.45
    output
    0.42
    POSITIVE LOGITS
    мила
    0.44
    экс
    0.40
    chloric
    0.38
     tassa
    0.38
    ξης
    0.37
    టింగ్
    0.36
     geschaffen
    0.36
     nécessaire
    0.36
     lump
    0.36
     disimpan
    0.36
    Act Density 0.001%

    No Known Activations