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

    Neuronpedia

    INDEX
    Explanations

    animals/pets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ْن
    -0.07
     Tek
    -0.07
     DX
    -0.06
     spanking
    -0.06
     Expert
    -0.06
    Sketch
    -0.06
     trees
    -0.06
    \Factory
    -0.06
     το
    -0.06
    .x
    -0.06
    POSITIVE LOGITS
     Assad
    0.07
     sec
    0.06
     Daisy
    0.06
     Влади
    0.06
     Wong
    0.06
    ?",
    0.06
    */↵
    0.06
     llam
    0.06
     cita
    0.06
    nám
    0.06
    Act Density 0.204%

    No Known Activations