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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions related to time

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

    temporal indicators with announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     précie
    -0.26
    Preguntas
    -0.25
    verhältnisse
    -0.24
     tromper
    -0.24
     étoient
    -0.24
     amada
    -0.23
     ressemb
    -0.22
    BitmapFactory
    -0.22
     laissé
    -0.22
    Bilan
    -0.21
    POSITIVE LOGITS
     $_=
    0.94
    ſſung
    0.93
     $_-
    0.90
     Weiſe
    0.90
     kaarangay
    0.89
    <unused20>
    0.89
    <unused41>
    0.89
    <unused15>
    0.89
    <unused43>
    0.89
    <pad>
    0.88
    Act Density 0.016%

    No Known Activations