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

    Neuronpedia

    INDEX
    Explanations

    programming syntax or constructs related to conditional statements and functions

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

    code syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.93
    niſſe
    -0.79
     فريبيس
    -0.77
     パンチラ
    -0.76
    ſicht
    -0.75
    <unused41>
    -0.74
    <unused52>
    -0.74
    <unused16>
    -0.74
    <unused74>
    -0.74
    [@BOS@]
    -0.73
    POSITIVE LOGITS
    ↵↵
    0.29
     Fritz
    0.27
                                   
    0.27
    txt
    0.26
     acus
    0.26
     Exactly
    0.25
     
    0.25
    早
    0.25
     Sadly
    0.25
    名
    0.24
    Act Density 0.132%

    No Known Activations