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

    Neuronpedia

    INDEX
    Explanations

    sex positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pan
    -0.08
          
↵
    -0.07
    वत
    -0.07
    #================================================================
    -0.07
    .attach
    -0.06
    invoke
    -0.06
     етап
    -0.06
    41
    -0.06
    istros
    -0.06
    .details
    -0.06
    POSITIVE LOGITS
    (LocalDate
    0.08
     Se
    0.07
     icy
    0.06
     instruction
    0.06
     خیابان
    0.06
     voir
    0.06
    -orders
    0.06
     объяс
    0.06
    ’ят
    0.06
    []){↵
    0.06
    Act Density 0.009%

    No Known Activations