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

    Neuronpedia

    INDEX
    Explanations

    o

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arded
    -0.06
     real
    -0.06
     incredible
    -0.06
    	label
    -0.06
     employer
    -0.06
    kk
    -0.06
    ату
    -0.06
     ()↵
    -0.06
     网
    -0.06
     mapped
    -0.06
    POSITIVE LOGITS
     dildo
    0.08
    ریان
    0.07
    LO
    0.07
    claimer
    0.07
    .WinControls
    0.07
     vibrator
    0.06
    .quality
    0.06
    ,O
    0.06
     розташ
    0.06
     Teddy
    0.06
    Act Density 0.057%

    No Known Activations