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

    Neuronpedia

    INDEX
    Explanations

    horizontal separators

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raiſ
    -0.76
     @{
    -0.75
     pleaſure
    -0.72
     Reſ
    -0.71
     viſ
    -0.70
     ſmall
    -0.69
     Chriftian
    -0.69
     purpoſe
    -0.68
     houſe
    -0.68
     Eſ
    -0.65
    POSITIVE LOGITS
     kasarigan
    0.63
    hopal
    0.57
     unknownFields
    0.54
     poko
    0.52
    JspWriter
    0.52
     Prasad
    0.47
     utafitiHapana
    0.47
     zac
    0.46
    ALLED
    0.46
    GOTREF
    0.46
    Act Density 0.017%

    No Known Activations