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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gaming and competition

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

    actions and scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ello
    -0.24
     initComponents
    -0.23
     tatou
    -0.23
    head
    -0.23
    ↵↵
    -0.22
     similarly
    -0.22
     again
    -0.21
     ryt
    -0.21
    <eos>
    -0.21
    iden
    -0.20
    POSITIVE LOGITS
    NameInMap
    0.96
    ########.
    0.90
    0.86
     noDo
    0.82
     незавершена
    0.81
    ſſung
    0.80
     kasarigan
    0.79
    <unused32>
    0.79
    <unused20>
    0.79
    [@BOS@]
    0.79
    Act Density 0.020%

    No Known Activations