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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    boru
    -0.06
     اجرا
    -0.06
    jerne
    -0.06
    ISyntaxException
    -0.06
     боку
    -0.06
    　j
    -0.06
     підтрим
    -0.06
    ναν
    -0.06
    rasing
    -0.06
     rugs
    -0.06
    POSITIVE LOGITS
    enez
    0.07
     highs
    0.07
    .")↵↵
    0.06
    .assertNot
    0.06
    not
    0.06
     evidently
    0.06
    ımızda
    0.06
     assert
    0.06
    elier
    0.06
     также
    0.06
    Act Density 0.293%

    No Known Activations