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

    Neuronpedia

    INDEX
    Explanations

    Billing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     neph
    -0.06
     thanking
    -0.06
     conce
    -0.06
     neutron
    -0.06
    ecta
    -0.06
    -sl
    -0.06
     greeted
    -0.06
     SCRIPT
    -0.06
     Twenty
    -0.06
    ptoms
    -0.06
    POSITIVE LOGITS
    اية
    0.07
    手机
    0.07
     edecek
    0.07
     []
    0.07
    <'
    0.06
    (^
    0.06
     ------------------------------------------------------------
    0.06
     []*
    0.06
    	else
    0.06
    >").
    0.06
    Act Density 0.000%

    No Known Activations