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

    Neuronpedia

    INDEX
    Explanations

    conversational markers and language usage in relation to fluency and understanding

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

    conversational language and expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     teacher
    -0.31
     English
    -0.31
    package
    -0.31
    teacher
    -0.28
     teachers
    -0.28
     raíces
    -0.27
    English
    -0.27
     doğal
    -0.27
     natural
    -0.26
     Teacher
    -0.26
    POSITIVE LOGITS
    ьаж
    0.82
     चीज़ों
    0.76
     estekak
    0.75
    UnusedPrivate
    0.74
     שוליים
    0.73
    expandindo
    0.72
    msgTypes
    0.71
    Tikang
    0.71
    VersionUID
    0.68
    enumii
    0.66
    Act Density 0.038%

    No Known Activations