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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to development and progress

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

    was was lost or conserved or increased

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     samfun
    -0.27
     condición
    -0.26
     eſt
    -0.25
     civilización
    -0.25
     žiad
    -0.25
     bluzka
    -0.24
     Presidencia
    -0.23
     housse
    -0.22
    QObject
    -0.22
     bocetos
    -0.22
    POSITIVE LOGITS
     kasarigan
    0.88
     queſto
    0.81
     estekak
    0.81
     snippetHide
    0.81
    <unused41>
    0.81
    ſicht
    0.81
    <unused14>
    0.80
    <unused8>
    0.80
    [@BOS@]
    0.80
    <unused1>
    0.80
    Act Density 0.105%

    No Known Activations