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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparisons and specifications about items or entities

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

    type is different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.59
    matchCondition
    -0.56
     Roskov
    -0.56
    expandindo
    -0.54
     noDo
    -0.53
    ContentAlignment
    -0.53
    ptonshire
    -0.51
    はじめに
    -0.50
    AccessorTable
    -0.49
    ]=>
    -0.49
    POSITIVE LOGITS
     variation
    0.36
    REDU
    0.34
     variant
    0.34
     inoxid
    0.34
    Variation
    0.33
     Fische
    0.33
     ester
    0.32
     Dure
    0.31
     cardia
    0.31
     Variation
    0.31
    Act Density 0.639%

    No Known Activations