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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations and boundaries

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

    "Of" or "within" indicating proximity or range

    np_acts-logits-general · gemini-2.0-flash

    beyond reach or scope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.77
    ModelAdmin
    -0.65
    <?
    -0.64
    ConstraintMaker
    -0.64
    principalColumn
    -0.61
    PYX
    -0.57
     esternos
    -0.57
     OMIT
    -0.57
    iastes
    -0.56
    CloseOperation
    -0.55
    POSITIVE LOGITS
     reach
    1.51
     scope
    1.25
     range
    1.21
     purview
    1.06
    reach
    1.04
     alcance
    1.02
     Reach
    1.01
    Reach
    0.97
     grasp
    0.96
    scope
    0.95
    Act Density 0.305%

    No Known Activations