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

    Neuronpedia

    INDEX
    Explanations

    instances of the "uparrow" symbol or similar upward arrows

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

    localization strings (gettext)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.38
     mis
    -0.36
     Gladiator
    -0.34
    <eos>
    -0.34
     Tutu
    -0.34
    Gön
    -0.34
     FetchType
    -0.34
    SupportActionBar
    -0.33
     Cuomo
    -0.33
    Abp
    -0.33
    POSITIVE LOGITS
    
    2.20
    
    0.77
    
    0.75
    <0x17>
    0.74
    
    0.74
    
    0.73
    
    0.71
    endphp
    0.67
    
    0.64
    
    0.62
    Act Density 0.002%

    No Known Activations