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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions and requirements for actions or outcomes

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

    to improve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.68
    WriteBarrier
    -0.59
     &___
    -0.54
     виправивши
    -0.52
     للاسماء
    -0.52
     MessageBoxIcon
    -0.51
    CppMethod
    -0.51
     للمعارف
    -0.50
     ujednoznacz
    -0.50
    NameInMap
    -0.49
    POSITIVE LOGITS
     Codable
    0.41
     sağlay
    0.40
    исленность
    0.34
     vivant
    0.32
     futuras
    0.31
    цездатний
    0.31
    skjaer
    0.31
    peaceful
    0.30
    cèse
    0.30
    engager
    0.30
    Act Density 0.027%

    No Known Activations