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

    Neuronpedia

    INDEX
    Explanations

    .objects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (T
    -0.06
    Bre
    -0.06
    aph
    -0.06
    (validate
    -0.06
    –and
    -0.06
    CString
    -0.06
     Leah
    -0.06
     pour
    -0.06
    426
    -0.06
    ===========↵
    -0.06
    POSITIVE LOGITS
    และการ
    0.07
     اک
    0.07
    εβ
    0.06
     пара
    0.06
     onc
    0.06
    	assertFalse
    0.06
    周年
    0.06
     piled
    0.06
     eleg
    0.06
     وع
    0.06
    Act Density 0.003%

    No Known Activations