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

    Neuronpedia

    INDEX
    Explanations

    instances of questions or tips within the text

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

    Questions, tips, notes, or disclaimers

    np_acts-logits-general · gemini-2.0-flash

    introducing queries and notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IUrlHelper
    -0.87
    EndProject
    -0.80
    encodeWith
    -0.74
    .},
    -0.72
    expandindo
    -0.71
    DrawerToggle
    -0.69
    InitVars
    -0.68
    ########.
    -0.66
    
    -0.66
     صوتيه
    -0.64
    POSITIVE LOGITS
    :
    0.68
     اینکه
    0.57
    Rè
    0.54
    FYI
    0.51
     note
    0.49
     sappi
    0.48
     Meski
    0.48
     hatır
    0.47
    ：
    0.47
     nho
    0.47
    Act Density 0.251%

    No Known Activations