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

    Neuronpedia

    INDEX
    Explanations

    fog and foghorn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     फार
    0.40
    สึก
    0.39
    摽
    0.39
    oreet
    0.38
    টিত
    0.37
    砟
    0.37
    风险
    0.37
    페이스
    0.37
    kita
    0.37
    洊
    0.36
    POSITIVE LOGITS
     fog
    0.99
    Fog
    0.96
    霧
    0.95
     foggy
    0.92
    fog
    0.89
    🌫
    0.87
    雾
    0.87
     Fog
    0.85
     misty
    0.79
     mist
    0.77
    Act Density 0.009%

    No Known Activations