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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation and special characters

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

    end of code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Night
    -0.42
    AUG
    -0.42
     Bug
    -0.42
     BUG
    -0.41
     conce
    -0.40
    YMS
    -0.40
     Ext
    -0.40
    ADHD
    -0.39
     daqui
    -0.39
    VersionUID
    -0.39
    POSITIVE LOGITS
    IntoConstraints
    0.57
    principalTable
    0.57
    Hentet
    0.50
    رشف
    0.48
     يتيمه
    0.47
    发表于
    0.46
    GOTREF
    0.45
    InjectAttribute
    0.44
    Jereo
    0.44
    RTCF
    0.43
    Act Density 0.006%

    No Known Activations