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

    Neuronpedia

    INDEX
    Explanations

    instances of actions involving filling things or making selections

    oai_token-act-pair · gemini-2.0-flash

    text with a focus on filling or filling-related actions

    np_token-act-pair-logits · gpt-4o-mini

    say "with"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Full
    -0.47
     Kammer
    -0.45
    enosine
    -0.45
     full
    -0.43
    Full
    -0.43
     يتيمه
    -0.41
    full
    -0.41
     pass
    -0.40
    diğini
    -0.39
     Do
    -0.39
    POSITIVE LOGITS
    __":
    0.81
     AssemblyTitle
    0.75
     المعيارى
    0.71
     ContentValues
    0.66
    GIVEREF
    0.66
    __':
    0.65
    XmlAccessType
    0.65
     typelib
    0.65
     Италијани
    0.63
     تضيفلها
    0.60
    Act Density 6.769%

    No Known Activations