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

    Neuronpedia

    INDEX
    Explanations

    say "th" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cub
    -0.07
     strict
    -0.07
     drafted
    -0.06
    Join
    -0.06
     tough
    -0.06
     hydrogen
    -0.06
     abst
    -0.06
     wine
    -0.06
     occurring
    -0.06
    Vs
    -0.06
    POSITIVE LOGITS
    0.07
    Generated
    0.06
    lant
    0.06
    .ColumnName
    0.06
     SUR
    0.06
    edor
    0.06
     BitConverter
    0.06
     českých
    0.06
     crippling
    0.06
     kendini
    0.06
    Act Density 0.133%

    No Known Activations