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

    Neuronpedia

    INDEX
    Explanations

    references to "name" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    variable or key name assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⅘
    -0.57
    soph
    -0.55
     Cec
    -0.53
     JSTOR
    -0.52
     Dij
    -0.51
     Rochester
    -0.51
     Pru
    -0.51
    pru
    -0.50
     Fletcher
    -0.50
    stiff
    -0.50
    POSITIVE LOGITS
     name
    1.97
     Name
    1.59
    Name
    1.54
     NAME
    1.54
    name
    1.53
     names
    1.51
    NAME
    1.41
     Names
    1.27
     Namen
    1.20
     이름
    1.19
    Act Density 0.064%

    No Known Activations