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

    Neuronpedia

    INDEX
    Explanations

    the word 'and' or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ourselves
    -0.67
     myself
    -0.46
    myself
    -0.44
    раздо
    -0.44
    likopter
    -0.44
    емся
    -0.43
    IsRequired
    -0.43
     нами
    -0.42
    ıyoruz
    -0.42
     próprias
    -0.40
    POSITIVE LOGITS
     he
    1.23
     she
    1.15
     they
    1.15
     он
    1.02
     она
    1.02
     они
    0.95
     він
    0.94
     वह
    0.93
     вона
    0.91
     вони
    0.88
    Act Density 3.663%

    No Known Activations