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

    Neuronpedia

    INDEX
    Explanations

    significant adjectives characterizing various qualities or states

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

    expressing opinions or evaluations

    np_acts-logits-general · gemini-2.0-flash

    descriptive adjectives and adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enough
    -0.68
    enough
    -0.68
     Enough
    -0.65
    Autoritní
    -0.62
    Enough
    -0.62
     suficientes
    -0.61
     sufficiently
    -0.60
    Personendaten
    -0.59
    \{\\
    -0.59
     suficiente
    -0.59
    POSITIVE LOGITS
    AndEndTag
    0.55
     indeed
    0.43
    RTRS
    0.39
    @[+][
    0.38
     AssemblyProduct
    0.36
    OCCURRED
    0.36
    Indeed
    0.35
     Indeed
    0.34
     hist
    0.34
     Zar
    0.34
    Act Density 0.510%

    No Known Activations