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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'seem' around 'to', as well as "R&B" in all caps

    oai_token-act-pair · gemini-2.0-flash

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     themſelves
    -0.63
     himſelf
    -0.58
     leſs
    -0.57
    ঁ
    -0.57
     Operator
    -0.56
     myſelf
    -0.56
     Operators
    -0.55
    ighted
    -0.54
     ſever
    -0.54
     faſt
    -0.54
    POSITIVE LOGITS
    +#+#
    0.98
    Personendaten
    0.81
    IsContent
    0.71
    imageio
    0.60
    featureID
    0.60
    AsUp
    0.59
    łaszcza
    0.57
    complexContent
    0.57
     lenker
    0.56
     Вікі
    0.56
    Act Density 0.833%

    No Known Activations