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

    Neuronpedia

    INDEX
    Explanations

    Answers, Agreements, Affirmations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    ZERO
    -0.06
     bx
    -0.06
    -0.06
     wreckage
    -0.06
    Wolf
    -0.06
    　　　　　 　
    -0.06
     summary
    -0.06
    _ball
    -0.06
    osex
    -0.06
    POSITIVE LOGITS
    。</
    0.07
    ีผ
    0.07
    ิทธ
    0.07
    ادن
    0.06
    UILD
    0.06
    edi
    0.06
     tokenizer
    0.06
     Arabic
    0.06
    πει
    0.06
    &P
    0.06
    Act Density 0.033%

    No Known Activations