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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     membrane
    -0.07
    انات
    -0.06
     rodz
    -0.06
    Jordan
    -0.06
                                    ↵
    -0.06
     IID
    -0.06
    Suite
    -0.06
    		    ↵
    -0.06
    ir
    -0.06
     comenz
    -0.06
    POSITIVE LOGITS
     知
    0.07
     بررسی
    0.07
    (dl
    0.06
    _ALERT
    0.06
    porte
    0.06
     OWN
    0.06
     SetProperty
    0.06
    知
    0.06
    urbed
    0.06
    phant
    0.06
    Act Density 0.060%

    No Known Activations