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

    Neuronpedia

    INDEX
    Explanations

    descriptive language that indicates quality or excellence

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

    following "that," "it," or "which"

    np_acts-logits-general · gemini-2.0-flash

    stand; stood; standing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.55
    imentel
    -0.52
    Scénario
    -0.51
    ANSA
    -0.46
    WRP
    -0.46
    rael
    -0.45
    ⮕
    -0.44
    ствовать
    -0.44
    formKey
    -0.43
    liesslich
    -0.43
    POSITIVE LOGITS
     stand
    2.56
     stood
    2.31
     stands
    2.29
     STAND
    2.20
     Stand
    2.17
    Stand
    2.11
    stand
    2.09
     standing
    1.96
     Stands
    1.90
    stands
    1.86
    Act Density 0.249%

    No Known Activations