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

    Neuronpedia

    INDEX
    Explanations

    is that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Will
    -0.07
    あった
    -0.07
    運動
    -0.06
    Eight
    -0.06
    uing
    -0.06
     []);↵
    -0.06
     Su
    -0.06
    Ended
    -0.06
    ），
    -0.06
    رير
    -0.06
    POSITIVE LOGITS
     спів
    0.07
    ارس
    0.07
    �
    0.07
     εφαρ
    0.07
    eshire
    0.07
     nanop
    0.06
     aftermarket
    0.06
    ерим
    0.06
     profes
    0.06
    광
    0.06
    Act Density 0.100%

    No Known Activations