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

    Neuronpedia

    INDEX
    Explanations

    terms related to research methodologies and data evaluation

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

    "across" follows the activating token

    np_acts-logits-general · gemini-2.0-flash

    verbs followed by across

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ويكيپيديا
    -0.63
     EClass
    -0.55
    uties
    -0.53
    farin
    -0.52
    rxjs
    -0.52
     wireType
    -0.52
     VIAF
    -0.51
     InputDecoration
    -0.51
    routeProvider
    -0.51
    initas
    -0.51
    POSITIVE LOGITS
     across
    3.22
     Across
    2.88
    across
    2.86
    Across
    2.75
     ACROSS
    2.62
     cross
    1.85
    cross
    1.69
    Cross
    1.67
     Cross
    1.59
    跨
    1.52
    Act Density 0.437%

    No Known Activations