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

    Neuronpedia

    INDEX
    Explanations

    sections of data separated by dividers or formatting lines

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

    numerical entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -1.21
     kasarigan
    -1.16
     незавершена
    -1.13
     queſto
    -1.05
    [@BOS@]
    -1.05
    <pad>
    -1.05
    <unused16>
    -1.04
    <unused17>
    -1.04
    <unused14>
    -1.04
    <unused3>
    -1.04
    POSITIVE LOGITS
    -
    0.51
    1
    0.48
    2
    0.45
    ,
    0.44
    ↵
    0.43
    0
    0.43
    :
    0.42
    /
    0.42
    <b>
    0.41
      
    0.41
    Act Density 0.246%

    No Known Activations