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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and definitions related to functions and variables

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

    defining, assuming, or denoting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portály
    -0.45
    oredCriteria
    -0.40
    argout
    -0.40
    IVEREF
    -0.40
    tagPool
    -0.33
    Organisateur
    -0.33
    canActivate
    -0.32
    Viited
    -0.31
    isContained
    -0.31
     Michael
    -0.31
    POSITIVE LOGITS
    ValueStyle
    0.71
    AndEndTag
    0.59
    цездатний
    0.53
    Assume
    0.52
    yeur
    0.51
     Assume
    0.50
    Assuming
    0.48
     Annahme
    0.48
     Assuming
    0.48
    toppers
    0.47
    Act Density 0.590%

    No Known Activations