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

    Neuronpedia

    INDEX
    Explanations

    long, detailed explanations of complex topics, particularly in a formal context such as laws, political theories, or historical events.

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

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pitfalls
    0.34
     parses
    0.32
    িনবার্গ
    0.31
     aberrations
    0.31
     universes
    0.29
     conund
    0.29
     constrain
    0.28
     dialects
    0.28
     appris
    0.28
     mols
    0.28
    POSITIVE LOGITS
     It
    0.53
     They
    0.45
     The
    0.40
     This
    0.39
     Specifically
    0.38
     Although
    0.37
    It
    0.36
     Basically
    0.36
     Some
    0.36
     While
    0.35
    Act Density 2.477%

    No Known Activations