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

    Neuronpedia

    INDEX
    Explanations

    words related to computation or coding processes like comparisons, replacements, or instantiation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ed
    -0.72
     tóxic
    -0.65
     Theſe
    -0.65
    able
    -0.64
    て
    -0.61
     obé
    -0.60
     rêver
    -0.60
     popolari
    -0.60
     mutate
    -0.59
     dreaming
    -0.57
    POSITIVE LOGITS
     SwiftUI
    0.92
    IActionResult
    0.90
    rollup
    0.85
     saites
    0.80
     estekak
    0.77
    )):
    0.75
    UIControlState
    0.75
    glEnd
    0.74
    ']))
    0.74
    createStatement
    0.73
    Act Density 0.092%

    No Known Activations