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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "remark" and its variations

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

    remarks of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dystop
    -0.46
    badlogic
    -0.43
     Uniti
    -0.41
    ぞ
    -0.40
    NOPQRST
    -0.40
    ufs
    -0.39
    userRepository
    -0.39
     dichoto
    -0.38
    Pä
    -0.38
    TypedDataSet
    -0.38
    POSITIVE LOGITS
    remarks
    3.30
    Remarks
    1.74
     remarks
    1.59
     Remarks
    1.59
     REMARKS
    1.48
    REMARKS
    1.48
    remark
    1.39
     remark
    1.24
    Remark
    1.23
     Remark
    1.16
    Act Density 0.001%

    No Known Activations