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

    Neuronpedia

    INDEX
    Explanations

    Javascript code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .showMessage
    -0.07
     FileAccess
    -0.06
    curity
    -0.06
    	from
    -0.06
     breaches
    -0.06
    .FirstName
    -0.06
    -‐
    -0.06
     Fountain
    -0.06
     rarely
    -0.06
     Ticaret
    -0.06
    POSITIVE LOGITS
     Đà
    0.07
     cuando
    0.07
    ُه
    0.06
     методи
    0.06
     orth
    0.06
     ),↵
    0.06
    ्फ
    0.06
    мет
    0.06
     yard
    0.06
    >"↵
    0.06
    Act Density 0.011%

    No Known Activations