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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dess
    -0.07
    .putString
    -0.07
    νη
    -0.06
     을
    -0.06
     kilometers
    -0.06
    चन
    -0.06
     lifted
    -0.06
    RG
    -0.06
    rowsable
    -0.06
    vido
    -0.06
    POSITIVE LOGITS
     ensures
    0.07
    ीख
    0.06
     Holocaust
    0.06
     Inch
    0.06
     Underground
    0.06
    {lng
    0.06
     dead
    0.06
     vých
    0.06
    .CONTENT
    0.06
     biochemical
    0.06
    Act Density 0.003%

    No Known Activations