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

    Neuronpedia

    INDEX
    Explanations

    year, seasons, atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Trash
    0.39
    צו
    0.36
     scrimmage
    0.36
    𒃲
    0.36
    一方面
    0.35
    केजी
    0.35
     швид
    0.34
    ებთ
    0.34
    ებულ
    0.34
    Cor
    0.34
    POSITIVE LOGITS
     Atmosphere
    0.46
     atmosphere
    0.43
     semana
    0.42
     atmospheres
    0.41
     anywhere
    0.41
     seasonal
    0.41
    闱
    0.40
     mily
    0.40
     year
    0.40
    ヘア
    0.40
    Act Density 0.020%

    No Known Activations