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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to safety and security measures

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

    safety information and measures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '{@
    -0.37
     King
    -0.37
     Clear
    -0.36
    jsdelivr
    -0.36
     Ge
    -0.36
    читан
    -0.35
    assertEqual
    -0.35
     a
    -0.35
     head
    -0.35
    cascade
    -0.35
    POSITIVE LOGITS
    сылкі
    0.66
    PhysRevD
    0.56
    ValueStyle
    0.54
     queſta
    0.52
     EconPapers
    0.50
    AccessorTable
    0.50
    !")
    0.48
    OGND
    0.47
    protoimpl
    0.47
    nezeu
    0.46
    Act Density 0.031%

    No Known Activations