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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection in relationships

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

    "is" followed by "that" or "almost"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dezelve
    -0.48
    arashtra
    -0.46
    országban
    -0.45
     sfida
    -0.44
    anjutnya
    -0.44
    aneously
    -0.44
    BibitemShut
    -0.44
    ніципа
    -0.44
     uitvo
    -0.44
    engibre
    -0.43
    POSITIVE LOGITS
    exitRule
    0.49
     незавершена
    0.47
    TableAdapter
    0.47
    tagHelperRunner
    0.46
     الحره
    0.45
    новниш
    0.44
     utafitiHapana
    0.43
    ConstraintMaker
    0.43
    URLException
    0.41
    FirebaseDatabase
    0.40
    Act Density 0.005%

    No Known Activations