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

    Neuronpedia

    INDEX
    Explanations

    HTML or XML attributes related to text formatting

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused68>
    -1.23
    <unused8>
    -1.23
    <pad>
    -1.23
    [@BOS@]
    -1.23
    <unused41>
    -1.23
    <unused42>
    -1.23
    <unused28>
    -1.23
    <unused23>
    -1.23
    <unused14>
    -1.23
    <unused16>
    -1.23
    POSITIVE LOGITS
    .
    0.61
     
    0.51
    ↵↵
    0.50
     $
    0.47
     $\
    0.46
    ,
    0.46
    ↵
    0.44
     L
    0.43
    s
    0.43
     F
    0.43
    Act Density 0.000%

    No Known Activations