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

    Neuronpedia

    INDEX
    Explanations

    references to hidden layers in neural network architecture

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

    hidden layer, nodes, or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.49
     élect
    -0.48
    Personensuche
    -0.46
    Зноскі
    -0.42
    oredCriteria
    -0.42
     jurk
    -0.41
    PhysRev
    -0.41
     strto
    -0.40
     Italijanski
    -0.40
    URLConnection
    -0.40
    POSITIVE LOGITS
     Hid
    0.68
     doInBackground
    0.64
    isHidden
    0.59
     HID
    0.59
     hid
    0.58
     Hide
    0.57
     Hidden
    0.57
     hide
    0.57
    Hid
    0.57
    HID
    0.56
    Act Density 0.014%

    No Known Activations