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

    Neuronpedia

    INDEX
    Explanations

    phrases related to containing or enclosing objects

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

    fill with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tanleria
    -0.48
     erfolgte
    -0.42
     heretofore
    -0.40
     împre
    -0.39
     begged
    -0.38
     występu
    -0.38
    chehen
    -0.37
     bislang
    -0.37
     Treue
    -0.37
     conductas
    -0.37
    POSITIVE LOGITS
     fill
    1.04
     filled
    1.00
    fill
    1.00
     Fill
    0.98
     filling
    0.95
     Filled
    0.95
    Fill
    0.93
     fills
    0.93
     Filling
    0.92
    filling
    0.91
    Act Density 0.020%

    No Known Activations