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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ansin
    -0.08
     sleepy
    -0.07
     Malagasy
    -0.07
     Τ
    -0.07
    kile
    -0.07
     Breton
    -0.07
     aufgenommen
    -0.07
    auftrag
    -0.07
    .change
    -0.07
     הט
    -0.07
    POSITIVE LOGITS
     regardless
    0.11
     irrespective
    0.10
     Regardless
    0.09
     universally
    0.08
    Minus
    0.08
    との
    0.07
     ورب
    0.07
     unabhängig
    0.07
     Minus
    0.07
     iff
    0.07
    Act Density 0.273%

    No Known Activations