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

    Neuronpedia

    INDEX
    Explanations

    references to security measures and breaches

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

    breaking into safes or doors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.70
    ConstraintMaker
    -0.54
     zoude
    -0.52
     dezelve
    -0.50
     viewType
    -0.49
    ↹
    -0.49
     argint
    -0.47
     câte
    -0.47
     MessageBoxIcon
    -0.47
     uitges
    -0.47
    POSITIVE LOGITS
     Baldwin
    0.41
     TestBed
    0.39
     breaching
    0.39
     sto
    0.39
     resisting
    0.38
    ObjectMeta
    0.38
     crime
    0.37
     kaz
    0.36
     Tür
    0.36
     door
    0.35
    Act Density 0.073%

    No Known Activations