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

    Neuronpedia

    INDEX
    Explanations

    phrases related to displaying or demonstrating actions or qualities

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

    showing something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.47
     Begegn
    -0.44
    CppMethod
    -0.44
     senhora
    -0.43
    pherals
    -0.41
    IEnumerator
    -0.41
     ře
    -0.41
    literals
    -0.38
     Töchter
    -0.38
     behalf
    -0.37
    POSITIVE LOGITS
     Show
    0.76
     Showing
    0.74
     showed
    0.73
     show
    0.71
     showing
    0.70
     Shows
    0.70
    SHOW
    0.69
    Showing
    0.68
     SHOW
    0.67
     Shown
    0.67
    Act Density 0.043%

    No Known Activations