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

    Neuronpedia

    INDEX
    Explanations

    elements related to classification and prediction tasks in data processing

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

    predicting binary classification outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.61
     يتيمه
    -0.51
    
    -0.50
    存于互联网档案馆
    -0.49
    NameInMap
    -0.49
    +#+#
    -0.47
    ✥
    -0.47
    <unused51>
    -0.46
    <unused8>
    -0.46
    [@BOS@]
    -0.46
    POSITIVE LOGITS
    AutoField
    0.48
     ProtoMessage
    0.47
    argmax
    0.37
    titleMargin
    0.33
    wahl
    0.33
    Diweddarwch
    0.33
     JUDGMENT
    0.33
    ENODE
    0.33
     karar
    0.33
    inference
    0.32
    Act Density 0.052%

    No Known Activations