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

    Neuronpedia

    INDEX
    Explanations

    phrases describing locations or opportunities for engagement

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

    place where to for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dovuto
    -0.42
     Milán
    -0.41
    เฉ
    -0.40
     pacar
    -0.40
    Referințe
    -0.40
     Saúde
    -0.39
     Agricultura
    -0.39
     flexível
    -0.39
     infek
    -0.39
     penggemar
    -0.39
    POSITIVE LOGITS
     place
    0.82
    place
    0.77
     places
    0.76
     Places
    0.75
    Places
    0.75
     PLACE
    0.69
    Place
    0.68
     Place
    0.67
    places
    0.67
     Tempat
    0.64
    Act Density 0.013%

    No Known Activations