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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENDING
    -0.65
     recognising
    -0.64
     agreeing
    -0.64
     sauvages
    -0.62
     recognizing
    -0.62
     wanting
    -0.61
     exporting
    -0.61
     preferring
    -0.60
     valuing
    -0.59
     informing
    -0.59
    POSITIVE LOGITS
    tvguidetime
    0.78
    Datuak
    0.68
     land
    0.59
    ]!='
    0.57
     sija
    0.55
     put
    0.54
     set
    0.54
    addCriterion
    0.52
     odkazy
    0.50
     lay
    0.50
    Act Density 0.002%

    No Known Activations