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

    Neuronpedia

    INDEX
    Explanations

    Academic/Formal publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thirty
    -0.07
     kHz
    -0.07
    adastrar
    -0.07
     verz
    -0.07
     przy
    -0.07
     Maiden
    -0.07
    Compra
    -0.07
    -sw
    -0.07
     grin
    -0.07
     Part
    -0.06
    POSITIVE LOGITS
    PT
    0.08
    JI
    0.07
    醌
    0.07
     dominated
    0.07
    ='#
    0.07
    -AA
    0.07
     alloc
    0.07
    תופעה
    0.07
    @Resource
    0.07
    nat
    0.06
    Act Density 0.202%

    No Known Activations