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

    Neuronpedia

    INDEX
    Explanations

    logical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jaw
    -0.08
     CAF
    -0.07
     confection
    -0.07
    istan
    -0.07
     dann
    -0.07
    യ്ക്ക്
    -0.07
     CPS
    -0.07
     Cayman
    -0.07
     بهدف
    -0.07
     محتر
    -0.07
    POSITIVE LOGITS
     lógico
    0.11
     logically
    0.10
     progression
    0.10
     Ablauf
    0.10
    顺
    0.08
     logisch
    0.08
     deduction
    0.08
     verloop
    0.08
    逻
    0.08
     Konsequ
    0.08
    Act Density 0.006%

    No Known Activations