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

    Neuronpedia

    INDEX
    Explanations

    expressions related to actions and consequences involving planning or taking responsibility

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

    Word after "one", "it", "a", or similar short words

    np_acts-logits-general · gemini-2.0-flash

    "such"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    -0.66
     unos
    -0.52
     awakeFromNib
    -0.51
     two
    -0.50
     some
    -0.48
    uncios
    -0.47
    Enllaços
    -0.46
    AddTagHelper
    -0.45
    ظه
    -0.45
    shafen
    -0.45
    POSITIVE LOGITS
     such
    0.81
    تقاوى
    0.80
    Such
    0.74
     solches
    0.74
    BeginContext
    0.72
     چنین
    0.69
     SUCH
    0.69
     Such
    0.68
     solch
    0.62
     ſuch
    0.61
    Act Density 0.303%

    No Known Activations