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

    Neuronpedia

    INDEX
    Explanations

    key phrases that indicate certainty or emphasis in statements

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

    yourself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.62
     utafitiHapana
    -0.49
    Filmografie
    -0.46
     desenli
    -0.43
     Persson
    -0.41
     Caruso
    -0.41
    Kariera
    -0.40
    CppCodeGen
    -0.40
    不说
    -0.39
     calientes
    -0.39
    POSITIVE LOGITS
    IndentedString
    0.47
     Yourself
    0.45
    yourself
    0.45
    protoimpl
    0.43
     yourself
    0.42
    Yourself
    0.42
    FirstResponder
    0.41
    Хьажоргаш
    0.40
    焉
    0.38
    themselves
    0.37
    Act Density 0.735%

    No Known Activations