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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals and publications

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

    International journals

    np_acts-logits-general · gemini-2.0-flash

    international journal publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.87
    таратура
    -0.73
     PopupWindow
    -0.59
     Wicidata
    -0.57
     Administrativna
    -0.57
    \{\\
    -0.55
    énario
    -0.53
     interesting
    -0.53
     مشين
    -0.53
    ră
    -0.52
    POSITIVE LOGITS
    IGI
    0.54
    IFI
    0.53
     IB
    0.52
    IRP
    0.52
     iArr
    0.51
    risch
    0.51
    IVI
    0.50
     IC
    0.50
     IP
    0.49
    msgTypes
    0.49
    Act Density 0.460%

    No Known Activations