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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "existing" or established items, systems, or conditions

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

    existing concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intptr
    -0.37
    SwingConstants
    -0.32
     global
    -0.31
     waterfront
    -0.29
     Tabor
    -0.29
     sandy
    -0.28
     ministros
    -0.28
    CheckedChanged
    -0.28
     por
    -0.28
    cosine
    -0.28
    POSITIVE LOGITS
     Existing
    0.96
    existing
    0.93
     existing
    0.91
    Existing
    0.90
     bestaande
    0.84
    already
    0.82
     existente
    0.82
    既存
    0.81
     existentes
    0.81
     Already
    0.81
    Act Density 0.047%

    No Known Activations