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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating components and processes within a systematic framework

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

    describes composition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    verwijspagina
    -0.61
     transfieras
    -0.60
    GEBURTS
    -0.52
    OGND
    -0.49
    Tikang
    -0.49
    SharedDtor
    -0.48
    Datuak
    -0.47
     שוליים
    -0.47
    новниш
    -0.46
     يتيمه
    -0.46
    POSITIVE LOGITS
     involves
    0.57
     consists
    0.53
     umfang
    0.52
     omfatt
    0.50
     comprises
    0.50
     entails
    0.49
     program
    0.49
     consiste
    0.49
     entail
    0.49
     involve
    0.48
    Act Density 0.043%

    No Known Activations