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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doğru
    -0.07
    ]},
    -0.06
     deck
    -0.06
     diaper
    -0.06
    "]');↵
    -0.06
     IPO
    -0.06
    word
    -0.06
     iyi
    -0.06
     hearings
    -0.06
     Viewing
    -0.05
    POSITIVE LOGITS
     шкі
    0.07
    Bo
    0.07
    Sig
    0.07
    Even
    0.06
     oku
    0.06
    istingu
    0.06
     REQUIRE
    0.06
    ENGINE
    0.06
    @return
    0.06
    MFLOAT
    0.06
    Act Density 0.016%

    No Known Activations