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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and special formatting characters

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

    msgstr ""

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.14
     betweenstory
    -1.12
    bootstrapcdn
    -1.08
    Personendaten
    -1.05
    -1.02
    ConstraintMaker
    -0.97
    <unused52>
    -0.96
    <unused68>
    -0.96
    <unused41>
    -0.96
    [@BOS@]
    -0.96
    POSITIVE LOGITS
    Reply
    0.51
    ↵↵
    0.50
    1
    0.48
    .
    0.48
    ↵↵↵
    0.44
    2
    0.43
    ↵
    0.43
    </tr>
    0.41
    </td>
    0.40
     
    0.40
    Act Density 0.001%

    No Known Activations