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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty and subjective interpretation

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

    in or off the ground

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.43
    chieht
    -0.43
     forState
    -0.42
     EClass
    -0.41
     său
    -0.40
    <%=
    -0.40
     Lordships
    -0.40
     createContext
    -0.40
     kapture
    -0.40
    RegistryLite
    -0.40
    POSITIVE LOGITS
    énario
    0.42
    الحياه
    0.40
    +#+#
    0.40
    Smooth
    0.38
    smooth
    0.38
    jamientos
    0.38
    WriteTagHelper
    0.37
     Smooth
    0.37
     smooth
    0.37
    Stdout
    0.37
    Act Density 0.450%

    No Known Activations