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

    Neuronpedia

    INDEX
    Explanations

    patterns of indentation in code blocks

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

    switch case default

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.64
     Италијани
    -0.63
     springfox
    -0.61
    onAttach
    -0.61
    MessageOf
    -0.60
     rodríguez
    -0.59
    iſten
    -0.59
    addPreferredGap
    -0.59
     saveiro
    -0.58
     ſtate
    -0.58
    POSITIVE LOGITS
     case
    0.38
     only
    0.36
     @"/
    0.36
     "
    0.33
     cases
    0.32
    texttt
    0.32
    ibb
    0.32
     such
    0.31
    <tr>
    0.31
     except
    0.30
    Act Density 0.005%

    No Known Activations