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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -aceutical"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Linux
    -0.07
     stab
    -0.06
    _sep
    -0.06
    ousands
    -0.06
    ingham
    -0.06
    .RESET
    -0.06
    .Imp
    -0.06
     devlet
    -0.06
    _python
    -0.06
     governments
    -0.06
    POSITIVE LOGITS
     доп
    0.07
     和
    0.07
    .labels
    0.07
     Země
    0.07
    業
    0.06
     kaps
    0.06
    Reusable
    0.06
    借
    0.06
    TriState
    0.06
     Rousse
    0.06
    Act Density 0.002%

    No Known Activations