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

    Neuronpedia

    INDEX
    Explanations

    temperature and weather events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     digesting
    0.40
    enger
    0.38
     xấu
    0.38
    Dev
    0.37
     heading
    0.37
    dif
    0.37
     discipline
    0.36
     Discipline
    0.36
    0.36
    discipline
    0.36
    POSITIVE LOGITS
    événement
    0.47
     Entrada
    0.44
    Peaks
    0.43
    Peak
    0.42
    सत
    0.41
     couper
    0.41
    పే
    0.40
    EVENT
    0.40
    Thermal
    0.40
     вход
    0.39
    Act Density 0.017%

    No Known Activations