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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the assessment or evaluation of situations and experiences

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

    words around punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     after
    -0.30
     réve
    -0.29
    .
    -0.29
     task
    -0.27
     asign
    -0.27
    ング
    -0.27
     Urlaub
    -0.26
    h
    -0.26
     tasks
    -0.25
     vuestro
    -0.25
    POSITIVE LOGITS
    ロウィン
    0.84
    WebElementEntity
    0.83
    <unused41>
    0.81
    <unused8>
    0.81
    <unused14>
    0.81
    <unused43>
    0.81
    <unused51>
    0.81
    <unused28>
    0.81
    [@BOS@]
    0.81
    <unused23>
    0.81
    Act Density 0.006%

    No Known Activations