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

    Neuronpedia

    INDEX
    Explanations

    cutting tools/instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     organizer
    -0.06
     groupBox
    -0.06
     also
    -0.06
    collapsed
    -0.06
    زراعة
    -0.06
    드
    -0.06
    }},↵
    -0.06
     policeman
    -0.06
    泖
    -0.06
     ślub
    -0.06
    POSITIVE LOGITS
    小姐姐
    0.07
    웨
    0.07
    indsight
    0.07
    ծ
    0.07
     аналог
    0.07
    Sequence
    0.07
    挽救
    0.07
     aprend
    0.06
     analyse
    0.06
    似乎是
    0.06
    Act Density 0.071%

    No Known Activations