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

    Neuronpedia

    INDEX
    Explanations

    Declaration of Independence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agse
    -0.08
    asian
    -0.07
     Pig
    -0.07
    iatamente
    -0.07
     teasing
    -0.07
     probing
    -0.07
    ย้อน
    -0.07
     taut
    -0.07
     humming
    -0.07
     gummy
    -0.07
    POSITIVE LOGITS
     своб
    0.10
     liberty
    0.10
     grievances
    0.09
     liberdade
    0.09
     rights
    0.09
     uintptr
    0.09
     freedoms
    0.08
     bolesti
    0.08
     liberties
    0.08
     comrades
    0.08
    Act Density 0.005%

    No Known Activations