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

    Neuronpedia

    INDEX
    Explanations

    references to variables or constants in mathematical contexts

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

    Why manufacturers, caught up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.12
    SequentialGroup
    -0.85
     wireType
    -0.84
     ujednoznacz
    -0.82
    exitRule
    -0.79
    tvguidetime
    -0.78
    DotNetBar
    -0.76
     useAppContext
    -0.74
    ChildScrollView
    -0.73
     AssemblyTitle
    -0.73
    POSITIVE LOGITS
    LOYEES
    0.26
     Italijanski
    0.23
     experto
    0.22
     expertos
    0.21
     ofrecerte
    0.20
    InjectAttribute
    0.20
     piłkarz
    0.19
    flü
    0.19
     Penge
    0.19
    CAPS
    0.18
    Act Density 0.003%

    No Known Activations