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

    Neuronpedia

    INDEX
    Explanations

    words associated with conversation, objectives, and purpose

    oai_token-act-pair · gemini-2.0-flash

    philosophical arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -0.93
    ########.
    -0.88
    GraphicsUnit
    -0.80
    DockStyle
    -0.73
     незавершена
    -0.72
    InjectAttribute
    -0.71
    AutoresizingMask
    -0.69
     Taktlose
    -0.67
    +#+#
    -0.67
    tagHelperRunner
    -0.66
    POSITIVE LOGITS
    formis
    0.45
     hoang
    0.43
    STRUCTOR
    0.43
    ülerin
    0.42
     S
    0.41
    PreferredItem
    0.41
    Interrupt
    0.40
     hongos
    0.39
    moor
    0.39
    PYX
    0.39
    Act Density 4.453%

    No Known Activations