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

    Neuronpedia

    INDEX
    Explanations

    exclamation marks and their contextual usage in visual elements

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

    Exclamations

    np_acts-logits-general · gemini-2.0-flash

    emphasis and list markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     незавершена
    -0.73
    
    -0.65
    UrlResolution
    -0.63
    Enllaces
    -0.61
    PickerController
    -0.61
    ings
    -0.58
    "):
    -0.57
     getItemCount
    -0.56
     محفوظة
    -0.55
    ation
    -0.54
    POSITIVE LOGITS
    ?!?
    1.25
    !!!!!!!
    1.17
    !!!!!!
    1.16
    !!!!!!!!!!
    1.16
    ?!?!
    1.13
    !!!!!!!!
    1.10
    !!!!!!!!!!!!!!!!
    1.07
     !
    0.99
    %!
    0.92
    -!
    0.87
    Act Density 0.165%

    No Known Activations