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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and definitions related to directed graphs

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

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.53
    WithIOException
    -0.38
    TypedDataSet
    -0.35
    博物
    -0.35
     nowhere
    -0.35
     ✭✭
    -0.34
    ContentAlignment
    -0.32
    Nowhere
    -0.31
    графия
    -0.30
     Sachin
    -0.30
    POSITIVE LOGITS
     typelib
    0.63
    Filmografie
    0.57
    ParseTree
    0.55
     mergeFrom
    0.54
    PointerException
    0.51
    BindView
    0.50
     gatherings
    0.49
     gathering
    0.49
     cuenca
    0.48
     caminar
    0.47
    Act Density 0.419%

    No Known Activations