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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <A
    -0.08
     rave
    -0.07
    renched
    -0.07
    ?",
    -0.07
    ,"\
    -0.07
    []"
    -0.07
    IELDS
    -0.07
    뉼
    -0.06
     radioButton
    -0.06
     Hint
    -0.06
    POSITIVE LOGITS
    After
    0.08
     Destiny
    0.07
    /type
    0.07
    š
    0.07
    什
    0.07
    Standard
    0.07
    	swap
    0.07
     clearance
    0.07
    ثان
    0.06
     digit
    0.06
    Act Density 0.000%

    No Known Activations