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

    Neuronpedia

    INDEX
    Explanations

    opinions and commentary

    np_max-act · gemini-2.0-flash

    It detects content-bearing verbs and descriptive adjectives—action or property words used in narratives.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    verbs about change

    np_max-act · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    Minor
    -0.07
    Only
    -0.07
    stim
    -0.07
    W
    -0.07
     cognition
    -0.06
    already
    -0.06
     jm
    -0.06
     disciple
    -0.06
    Nobody
    -0.06
    نج
    -0.06
    POSITIVE LOGITS
    ="";
↵
    0.07
    MethodBeat
    0.06
    esium
    0.06
     MutableLiveData
    0.06
    .radio
    0.06
    .getvalue
    0.06
    oftware
    0.06
     मल
    0.06
    acción
    0.06
    InTheDocument
    0.06
    Act Density 0.977%

    No Known Activations