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

    Neuronpedia

    INDEX
    Explanations

    form

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uchs
    -0.07
    迪
    -0.06
    threat
    -0.06
     operations
    -0.06
    -fl
    -0.06
     там
    -0.06
    Sen
    -0.06
    visit
    -0.06
    ्बन
    -0.06
    NSDate
    -0.06
    POSITIVE LOGITS
     form
    0.07
    atform
    0.07
    	Editor
    0.07
     lush
    0.06
     tạp
    0.06
    .Resource
    0.06
    	http
    0.06
     Griffith
    0.06
    override
    0.06
    baar
    0.06
    Act Density 0.009%

    No Known Activations