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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     we
    -0.07
    ">$
    -0.06
    sequences
    -0.06
    _GREEN
    -0.06
    ,strong
    -0.06
    ijke
    -0.06
     rval
    -0.06
     исключ
    -0.06
     SetUp
    -0.06
     ситуа
    -0.06
    POSITIVE LOGITS
    rai
    0.07
    (vs
    0.07
    ンブ
    0.06
     chocolate
    0.06
     مرحله
    0.06
     slump
    0.06
    ick
    0.06
     erre
    0.06
     nef
    0.06
    alesce
    0.06
    Act Density 0.021%

    No Known Activations